# Umesh Malik - Software Engineer & AI Builder > AI Engineer building GenAI applications, LLM-powered products, and scalable software systems. > 5+ years of production engineering at Expedia Group, Tekion Corp, and BYJU'S. > Technical blogger writing about AI, GenAI, LLMs, RAG, agentic workflows, and software engineering. > For the extended version of this file, see: https://umesh-malik.com/llms-full.txt > Every page on this site has a Markdown rendering: append `.md` to its path > (the homepage is at https://umesh-malik.com/index.md). All links below already point there. ## Quick Facts - Name: Umesh Malik - Role: Software Engineer & AI Builder - Company: Expedia Group - Focus: AI Engineering, GenAI, LLMs, RAG Pipelines, Agentic Workflows - Location: Gurugram, Haryana, India - Email: ask@umesh-malik.com - LinkedIn: https://linkedin.com/in/umesh-malik - GitHub: https://github.com/Umeshmalik - Website: https://umesh-malik.com - Blog: https://umesh-malik.com/blog - Experience: 5+ years production engineering - Education: MCA & BCA in Computer Science ## AI & GenAI Skills AI: Large Language Models, RAG Pipelines, Agentic Workflows, Prompt Engineering, LangChain, Vector Databases, Claude API, OpenAI API, MCP (Model Context Protocol) Frontend: React, TypeScript, JavaScript (ES6+), Next.js, SvelteKit, Vue.js, TailwindCSS Backend: Node.js, Python, Express.js, MongoDB, PostgreSQL, REST APIs, GraphQL Architecture: System Design, AI/ML Pipeline Design, Microfrontend Architecture, Performance Optimization ## Current Role (June 2024 - Present) Software Development Engineer 2 at Expedia Group - Core engineer for Workflow Orchestration Platform — infrastructure for AI-driven automation - Migrated legacy Vue.js to React (3x velocity improvement) - Built reusable component libraries - Created visual workflow diagram editor ## Previous Experience ### Tekion Corp - Software Engineer (April 2023 - May 2024) - Rebuilt Finance & Insurance module for automotive dealerships - Implemented internationalization and accessibility (WCAG) ### BYJU'S - Module Lead (March 2022 - April 2023) - Led Order & Payment Validation modules ($10M+ monthly transactions) - Built Pincode Management system (19,000+ entries) - Mentored junior engineers ### BYJU'S - Associate Software Engineer (July 2021 - February 2022) - Built Wallet and Bonus Points modules - Performer of the Quarter (January 2022) ## Key Projects 1. AI-Powered RAG SaaS Platform: Full-stack RAG app with vector embeddings, semantic search, and conversational AI 2. Agentic AI Workflow Engine: Autonomous agent system with task decomposition and MCP integration 3. Workflow Orchestration Platform (Expedia): Enterprise workflow editor — foundation for AI automation 4. Payment System (BYJU'S): High-reliability payment processing ($10M+ monthly, 99.9% uptime) 5. AI-Optimized Portfolio (Open Source): SvelteKit site with llms.txt, structured data, AI-indexed content ## Blog Posts (89 articles) - [Fix slow LLM inference in macOS VMs: 12.6 → 207 tok/s](https://umesh-malik.com/blog/fix-slow-llm-inference-macos-vms.md) (2026-08-11): LLM inference in macOS VMs collapses to 12.63 tok/s because the guest reports GPU family 5 and llama.cpp drops - [Learn Complex Topics With Claude Code: Build a Simulation, Not Notes](https://umesh-malik.com/blog/learn-complex-topics-claude-code-simulations.md) (2026-08-11): Learn complex topics with Claude Code by building a small simulation of the mechanism: the 4-step loop, the fa - [Run Muse Glimmer 30B locally: 55GB shrinks to under 20GB](https://umesh-malik.com/blog/run-muse-glimmer-30b-locally.md) (2026-08-11): How to run Muse Glimmer 30B locally: the K-Quant setup that fits a single 24GB GPU, the drafter model that tri - [How to Test an LLM's Knowledge Cutoff: Opus 5's May Claim Falls Short](https://umesh-malik.com/blog/testing-llm-knowledge-cutoffs-opus-5.md) (2026-08-11): Here's how to test an LLM's knowledge cutoff with three reproducible probes — the method showing Opus 5 claims - [How to sandbox an AI agent: 10 of 122 eval runs went rogue](https://umesh-malik.com/blog/sandbox-ai-agent-internet-access.md) (2026-08-08): AISI logged 19 unsanctioned actions across 122 cyber-eval runs. How to sandbox an AI agent at the network laye - [vLLM throughput tuning: configure these four flags, not a bigger GPU](https://umesh-malik.com/blog/vllm-throughput-tuning-flags.md) (2026-08-08): vLLM throughput tuning starts with KV cache blocks, not a bigger GPU. The four flags that decide your tokens/s - [Configuring AI Agent Permissions: Humans Miss 1 in 3 Threats](https://umesh-malik.com/blog/ai-agent-permissions-approval-fatigue.md) (2026-08-07): 409,000 approve/deny decisions show humans miss 1 in 3 agent threats, and 52.5% of npm-shaped exfiltration. Th - [Set up AI Gateway for Workers AI: one argument, every call logged](https://umesh-malik.com/blog/ai-gateway-for-workers-ai.md) (2026-08-07): AI Gateway for Workers AI is now one argument on env.AI.run. What it logs instantly, why caching stays off unt - [Fix the Datasette SQL Injection: Why execute-sql Won't Save You](https://umesh-malik.com/blog/datasette-sql-injection-patch.md) (2026-08-07): The Datasette SQL injection patched in 1.0a38 and 0.65.3 leaks private tables via unescaped filter columns. Th - [How to Make Your Site Agent-Readable: 4 Layers, One Worker](https://umesh-malik.com/blog/make-your-site-agent-readable.md) (2026-08-07): Make your site agent-readable in four layers — readable, discoverable, callable, payable. Three are build-time - [Fix your agent tool instructions: GitHub's 20% review-cost cut](https://umesh-malik.com/blog/writing-agent-tool-instructions.md) (2026-08-07): Agent tool instructions decide what your agent costs. GitHub kept the same grep/glob/view toolset, rewrote the - [Ads for AI Agents: TIME Serves Crawlers a Different Site](https://umesh-malik.com/blog/ads-for-ai-agents-time-markdown-crawlers.md) (2026-08-06): Ads for AI agents are live. TIME serves crawlers a 42 KB markdown site with sponsored blocks; humans and Googl - [Configure Dependabot grouped updates: one PR a month, CVEs instant](https://umesh-malik.com/blog/dependabot-grouped-updates-cut-pr-noise.md) (2026-08-06): Dependabot grouped updates fold a month of version bumps into one pull request while CVE fixes still land same - [Run agent tool calls in parallel: 10 turns become 2 DAG levels](https://umesh-malik.com/blog/parallel-agent-tool-calls-dag-harness.md) (2026-08-06): Run agent tool calls in parallel by swapping the loop for a DAG planner: ten round trips become two levels, pl - [Reinforcement Fine-Tuning: When a 4B Model Beats GPT-5.6](https://umesh-malik.com/blog/reinforcement-fine-tuning-small-models-retrieval.md) (2026-08-06): Reinforcement fine-tuning let a 4B open model match GPT-5.6 Sol on retrieval at 100x lower cost. How RFT works - [Run CI/CD on Cloudflare Workflows: deploy in 18 lines, 33 free runs](https://umesh-malik.com/blog/run-cicd-cloudflare-workflows.md) (2026-08-06): Run CI/CD on Cloudflare Workflows and a GitHub Actions YAML becomes 18 lines of TypeScript. Which meter bills - [Rust LLM Policy: Use AI to Review, Not to Create](https://umesh-malik.com/blog/rust-llm-policy-ai-generated-code.md) (2026-08-06): The Rust LLM policy bans AI-created code and prose but allows AI review, analysis, and bug-finding. Here's the - [Agent Harness Design: Why an ARC-AGI-3 Score Tripled](https://umesh-malik.com/blog/agent-harness-design-arc-agi-3.md) (2026-08-05): Agent harness design decided a benchmark: OpenAI's ARC-AGI-3 score went 13.3% → 38.3% with zero model changes. - [Insider Threat Offboarding Controls: The Apple v. OpenAI Lesson](https://umesh-malik.com/blog/insider-threat-offboarding-controls.md) (2026-08-05): Insider threat offboarding controls, read through Apple v. OpenAI: retained devices, live access, and why weak - [LLM Abuse Detection: What OpenAI's Scam Ban Reveals](https://umesh-malik.com/blog/llm-abuse-detection-openai-scam-network.md) (2026-08-05): LLM abuse detection failed at the message level and worked at the account level. OpenAI's Cambodia scam ban sh - [MCP Write Controls: Lessons from Cloudflare WriteGuard](https://umesh-malik.com/blog/mcp-write-controls-cloudflare-writeguard.md) (2026-08-05): MCP write controls decide what your agents can break. Cloudflare's WriteGuard shows the pattern: per-tool risk - [How to Secure MCP Write Tools: Cloudflare's WriteGuard Lesson](https://umesh-malik.com/blog/secure-mcp-write-tools-writeguard.md) (2026-08-05): How to secure MCP write tools: the spec puts confirmation on the client — the one layer you don't control. Clo - [Cloudflare Wallets and x402: How AI Agents Pay for APIs](https://umesh-malik.com/blog/cloudflare-wallets-x402-agent-payments.md) (2026-08-04): Cloudflare Wallets and x402 explained: how AI agents get a spending identity, how HTTP 402 payments work, and - [Fake CVE Reports: 54 of 55 SQLite Advisories Were AI Slop](https://umesh-malik.com/blog/fake-cve-reports-ai-slop-sqlite.md) (2026-08-04): Fake CVE reports are now cheaper to write than to disprove. JFrog found 54 of 55 SQLite advisories fabricated - [LLM Eval Framework: Grade Prompts, Models and Harnesses](https://umesh-malik.com/blog/llm-eval-framework-smevals.md) (2026-08-04): An LLM eval framework turns vibes into scores. How smevals structures tasks, configs, runners and graders — an - [Production-Grade AI Agents: The Vibe-to-Live Gap](https://umesh-malik.com/blog/production-grade-ai-agents-vibe-to-live-gap.md) (2026-08-04): Production-grade AI agents need more than a working demo. 353,000 signed up to learn agents; 6,000 shipped a c - [Run 70B LLM on 4GB GPU: AirLLM's Real Tradeoff](https://umesh-malik.com/blog/run-70b-llm-on-4gb-gpu-airllm.md) (2026-08-04): Run 70B LLM on 4GB GPU hardware with AirLLM's layer-by-layer inference. The VRAM math is real — you just pay f - [Agent-to-Human Delegation: Why Your AI Shouldn't DM Coworkers](https://umesh-malik.com/blog/agent-to-human-delegation.md) (2026-08-03): Agent-to-human delegation is the pattern nobody designed for: your AI messaging a coworker. Why it lands badly - [Explorative Modeling: Train on the Best of K Guesses](https://umesh-malik.com/blog/explorative-modeling-train-on-best-of-k.md) (2026-08-02): Explorative modeling factors the training loop instead of generation: sample K guesses, train only on the best - [DeepSeek V4 Flash 0731 Benchmarks: 13B Active Beats 1.6T](https://umesh-malik.com/blog/deepseek-v4-flash-0731-benchmarks.md) (2026-08-01): DeepSeek V4 Flash 0731 benchmarks: same 284B/13B architecture as the preview, re-post-trained only — and it be - [How to Increase SEO Traffic in the AI Era: 10 Techniques (2026)](https://umesh-malik.com/blog/increase-seo-traffic-ai-era-techniques.md) (2026-07-29): How to increase SEO traffic in the AI era: 10 genuine, white-hat techniques anyone can use to earn clicks and - [SEO in the AI Era: The 2026 GEO Playbook for Winning AI Search Traffic](https://umesh-malik.com/blog/seo-in-the-ai-era-geo-playbook.md) (2026-07-27): SEO in the AI era: what actually changed, why clicks fell 60%, and the GEO playbook to earn traffic from ChatG - [Claude Opus 5 Migration: The Two API Changes That Break Your Code](https://umesh-malik.com/blog/claude-opus-5-guide.md) (2026-07-24): Two API changes break a Claude Opus 5 migration, and the effort parameter needs re-sweeping, not reusing. The - [Build a RAG Chatbot in Next.js: Retrieval, Streaming & Citations (2026)](https://umesh-malik.com/blog/rag-chatbot-nextjs-guide.md) (2026-07-21): Build a RAG chatbot in Next.js with the AI SDK: embed the query, search pgvector, stream a grounded answer wit - [React Server Components in 2026: The Mental Model, the use client Boundary & When Not to Use Them](https://umesh-malik.com/blog/react-server-components-guide.md) (2026-07-21): React Server Components in 2026: the mental model that finally clicks, the use client boundary rules, and when - [Vercel AI SDK in Production: Streaming, Tool-Calling & the Gotchas Nobody Tells You (2026)](https://umesh-malik.com/blog/vercel-ai-sdk-production-guide.md) (2026-07-21): Vercel AI SDK in production: streaming, tool-calling, aborting generations, error retry UX, rate limiting, and - [Kimi K3 vs Claude Fable 5: When the Open Model Is Worth the Switch](https://umesh-malik.com/blog/kimi-k3-vs-claude-fable-5.md) (2026-07-19): Kimi K3 beats Claude Fable 5 on cost by a wide margin and loses on agentic tasks. The benchmarks that decide i - [Streaming HTML Out of Order Without JavaScript (2026)](https://umesh-malik.com/blog/streaming-html-out-of-order-without-javascript.md) (2026-07-14): Streaming HTML out of order without JavaScript: how Declarative Partial Updates and Declarative Shadow DOM reo - [ChatGPT Apps SDK and the Super App Reform: How Apps in ChatGPT Work (2026)](https://umesh-malik.com/blog/chatgpt-apps-sdk-super-app-guide.md) (2026-07-11): The ChatGPT Apps SDK explained: how apps in ChatGPT work, why it's built on MCP, who the launch partners are, - [GPT-5.6 Sol vs Terra vs Luna: The Routing Strategy That Cuts Cost](https://umesh-malik.com/blog/gpt-5-6-sol-vs-terra-vs-luna.md) (2026-07-11): GPT-5.6 Sol vs Terra vs Luna compared on price, coding, latency, and cost per task — plus a routing strategy t - [GPT-5.6 API: Pricing, Thinking Modes, and the Shared Context Trap](https://umesh-malik.com/blog/openai-gpt-5-6-sol-terra-luna-guide.md) (2026-07-11): GPT-5.6 API pricing ($1–$30/1M), the Ultra and Max thinking modes, and a 1.05M context window that is shared — - [How to Build Enterprise-Grade AI Agents for Free (MaxKB, 2026)](https://umesh-malik.com/blog/build-enterprise-ai-agents-free.md) (2026-07-08): How to build enterprise-grade AI agents for free in 2026: a hands-on MaxKB + local LLM guide to RAG precision, - [HTTP QUERY Method Explained (RFC 10008): GET vs POST](https://umesh-malik.com/blog/http-query-method-rfc-10008-guide.md) (2026-07-03): RFC 10008's HTTP QUERY method is safe, idempotent, and cacheable like GET but carries a body like POST. What i - [Claude Fable 5: Capabilities, Cost & When to Use It (2026)](https://umesh-malik.com/blog/claude-fable-5-guide.md) (2026-07-02): Claude Fable 5 is Anthropic's most capable model yet. The honest deep-dive: capabilities, the $10/$50 cost mat - [Claude Sonnet 5 for Coding: The Tokenizer Change That Moves Your Bill](https://umesh-malik.com/blog/claude-sonnet-5-guide.md) (2026-07-01): Claude Sonnet 5 for coding lands near Opus level at Sonnet prices — until the tokenizer change moves your bill - [Is Claude Code Auto Mode Reliable in Production? A Field Report](https://umesh-malik.com/blog/claude-code-auto-mode-production-field-report.md) (2026-06-25): I ran Claude Code auto mode in production for a week — where it's reliable, where it broke, real token costs f - [Claude Code vs Cursor for Production: A Shipping Engineer's Field Report (2026)](https://umesh-malik.com/blog/claude-code-vs-cursor-production-work-2026.md) (2026-06-25): Claude Code vs Cursor for production, field-tested on real shipping tasks: a working engineer's decision table - [Can You Use Claude Code and Codex for Free? Honest 2026 Guide](https://umesh-malik.com/blog/use-claude-code-codex-for-free.md) (2026-06-23): The honest answer to using Claude Code and Codex for free in 2026: what's truly $0, what isn't, the best free - [FastAPI Finally Has Native SPA Support: app.frontend() Explained](https://umesh-malik.com/blog/fastapi-spa-app-frontend-explained.md) (2026-06-21): FastAPI 0.138.0 ships app.frontend() — a native way to serve React, Vue, and Svelte SPA builds. How it works, - [Agentic Browsing in PageSpeed Insights: How to Make Your Website AI-Ready (2026)](https://umesh-malik.com/blog/agentic-browsing-pagespeed-ai-ready.md) (2026-06-19): Agentic browsing in PageSpeed Insights grades your site for AI agents, not just humans. What the category chec - [Why 77% of Autonomous AI Agents Never Reach Production (2026)](https://umesh-malik.com/blog/autonomous-ai-agents-production-gap-2026.md) (2026-06-14): Only 23% of autonomous AI agents reach production in 2026. The demo-to-production gap, why agents fail, and th - [How I Built a Full Audio/Video Streaming Microservice in One Day with Claude Fable 5 Auto Mode](https://umesh-malik.com/blog/claude-fable-5-streaming-microservice-one-day.md) (2026-06-13): Claude Fable 5 in auto mode built my entire HLS streaming microservice in under a day — AWS infra, security, b - [Build a RAG Pipeline From Scratch: Production Patterns That Matter](https://umesh-malik.com/blog/build-rag-pipeline-from-scratch.md) (2026-06-08): Build a RAG pipeline from scratch: chunking, embeddings, retrieval, reranking, grounded generation, and the pr - [Cursor vs Claude Code vs Copilot (2026): Which Tool for What](https://umesh-malik.com/blog/cursor-vs-claude-code-vs-copilot.md) (2026-06-08): Cursor vs Claude Code vs Copilot in 2026 — how they actually differ in model, workflow, and autonomy, and whic - [Deploy an MCP Server on Cloudflare Workers (Free, at the Edge)](https://umesh-malik.com/blog/deploy-mcp-server-cloudflare-workers.md) (2026-06-08): Deploy an MCP server on Cloudflare Workers: wrangler.toml, the run_worker_first model, routing /mcp, local tes - [How to Build an MCP Server: A Step-by-Step Guide (2026)](https://umesh-malik.com/blog/how-to-build-mcp-server.md) (2026-06-08): How to build an MCP server, step by step: JSON-RPC 2.0, the Streamable HTTP transport, typed tools, and agent - [How to Write a CLAUDE.md That Actually Helps](https://umesh-malik.com/blog/how-to-write-claude-md.md) (2026-06-08): How to write a CLAUDE.md that actually helps Claude Code: what to include, what to leave out, a real structure - [How to Switch Between Multiple Claude Code Accounts Without Re-Logging In (claude-swap Guide)](https://umesh-malik.com/blog/claude-swap-multi-account-switcher-guide.md) (2026-05-30): claude-swap is an open-source CLI that switches Claude Code accounts in seconds — no browser re-login. How it - [Claude Code Leak 2026: What Escaped and What Didn't](https://umesh-malik.com/blog/claude-code-leak-march-2026.md) (2026-04-02): The Claude Code leak of March 31, 2026, explained: what the source-map exposure revealed, Anthropic's DMCA swe - [Axios Compromised on npm: 1.14.1, 0.30.4 Drop a Cross-Platform RAT](https://umesh-malik.com/blog/axios-compromised-npm-cross-platform-rat.md) (2026-03-31): Axios compromised on npm on March 31, 2026: versions 1.14.1 and 0.30.4 dropped a cross-platform RAT. Verified - [Nvidia OpenClaw Explained: Your AI Agent Strategy (GTC 2026)](https://umesh-malik.com/blog/nvidia-openclaw-strategy-ai-agent-plan.md) (2026-03-17): At GTC 2026, Jensen Huang said every company needs a Nvidia OpenClaw strategy. Here is what it means and what - [ChatGPT Adult Mode: Is It Live Yet? (Status Explained)](https://umesh-malik.com/blog/chatgpt-adult-mode-delay-guide.md) (2026-03-16): ChatGPT adult mode is still delayed — OpenAI's official status, what the feature would allow, why it was pushe - [ChatGPT Interactive Math and Science Visuals: What to Know](https://umesh-malik.com/blog/chatgpt-interactive-math-science-visuals-guide.md) (2026-03-12): ChatGPT interactive math and science visuals launched in March 2026: how the new learning modules work, who ge - [Claude Code Review: How It Works, Pricing & Setup](https://umesh-malik.com/blog/anthropic-code-review-claude-code-guide.md) (2026-03-10): Anthropic's Claude Code Review runs multi-agent PR reviews for $15-$25 each. How it works, pricing, REVIEW.md - [Agentic AI Security: The New Enterprise Control Model](https://umesh-malik.com/blog/agentic-ai-enterprise-security-model.md) (2026-03-09): Agentic AI security breaks the old enterprise trust model. How to fix identity, delegated authority, prompt in - [GPT-5.4 for Agents: Computer Use, MCP Tool Calls, and Real Pricing](https://umesh-malik.com/blog/openai-gpt-5-4-complete-guide.md) (2026-03-06): GPT-5.4's native computer use and MCP tool calls are the real upgrade for agents. What holds up in a loop, wha - [OpenAI GPT-5.3 Instant: 26.8% Fewer Hallucinations, Reduced Refusals, and Better Web Answers](https://umesh-malik.com/blog/openai-gpt-5-3-instant-fewer-refusals-better-answers.md) (2026-03-04): GPT-5.3 Instant brings 26.8% fewer hallucinations, fewer needless refusals, and better web-sourced answers — w - [DeepSeek V4 vs US AI Models: Benchmarks, Architecture, and What It Means for the Industry](https://umesh-malik.com/blog/deepseek-v4-release-challenge-us-ai-rivals.md) (2026-03-01): DeepSeek V4 is expected in early March 2026. Here is what is confirmed, what remains unverified, and how it ch - [RAG vs Fine-Tuning for LLMs in 2026: A Production Decision Framework With Real Tradeoffs](https://umesh-malik.com/blog/rag-vs-fine-tuning-llms-2026.md) (2026-02-28): RAG vs fine-tuning for LLMs in 2026: a practical decision framework covering architecture tradeoffs, cost, lat - [Figma to React With OpenAI Codex: A 2026 Guide](https://umesh-malik.com/blog/figma-codex-react-2026.md) (2026-02-27): A 2026 guide to Figma to React conversion with OpenAI Codex: setup, prompts, component structure, and real pro - [Cloudflare viNext: The $1,100 Next.js-on-Vite Rebuild](https://umesh-malik.com/blog/cloudflare-vinext-next-js-vite-revolution.md) (2026-02-25): Cloudflare viNext rebuilt Next.js on Vite for $1,100 in 7 days: 4.4x faster builds, 57% smaller bundles, alrea - [AI Model Distillation: Inside the $100M Claude Heist](https://umesh-malik.com/blog/anthropic-detecting-preventing-distillation-attacks.md) (2026-02-24): Anthropic exposes an AI model distillation attack by DeepSeek, Moonshot, and MiniMax: 16 million exchanges, 24 - [Qwen3-Coder: Run an 80B-Parameter LLM on Your Desktop](https://umesh-malik.com/blog/local-llm-coding-revolution-qwen3-coder-desktop.md) (2026-02-22): Qwen3-Coder runs 80B parameters on a desktop with only 3B active per token — and plugs into Claude Code. Why t - [Spec-Driven Development for AI Agents (Addy Osmani)](https://umesh-malik.com/blog/spec-driven-development-ai-agents-addy-osmani.md) (2026-02-21): Why AI coding agent prompts fail — and how spec-driven development fixes it, per Addy Osmani's 5-principle fra - [Node.js Pointer Compression: Cut Heap Memory ~50%](https://umesh-malik.com/blog/nodejs-memory-cut-in-half-pointer-compression.md) (2026-02-18): V8 pointer compression finally lands in Node.js: one Docker image swap cuts heap memory ~50%, improves P99 lat - [AGENTS.md Files Don't Work the Way You Think — A 138-Repo Study](https://umesh-malik.com/blog/agents-md-ai-coding-agents-study.md) (2026-02-17): A 138-repo study: AGENTS.md files hurt performance by 2-3% and raised costs 20%+. What the research found — an - [Docker Swarm vs Kubernetes: $166/yr Beats a $200K Cluster](https://umesh-malik.com/blog/docker-swarm-vs-kubernetes-166-dollar-reality-check.md) (2026-02-17): Docker Swarm vs Kubernetes: a live SaaS runs for $166/year with zero crashes in 10 years, while the average Ku - [Seedance 2.0: The Two-Line Prompt That Broke Hollywood](https://umesh-malik.com/blog/seedance-2-hollywood-ai-copyright-crisis.md) (2026-02-16): ByteDance's Seedance 2.0 made a photorealistic Tom Cruise vs Brad Pitt fight from a two-line prompt — igniting - [AI Agent Attacks Developer After Matplotlib PR Rejection — Full Story](https://umesh-malik.com/blog/ai-agent-attacks-developer-matplotlib-open-source.md) (2026-02-15): The first documented AI agent attack on an open-source maintainer: rejected on a matplotlib PR, the bot publis - [Node.js Backend for Frontend Developers: A Practical Guide](https://umesh-malik.com/blog/nodejs-backend-for-frontend-developers.md) (2026-02-10): A frontend developer's guide to building a Node.js backend: Express, REST APIs, middleware, databases, auth, a - [Frontend Career Growth: From Junior to Senior Engineer](https://umesh-malik.com/blog/frontend-career-growth-junior-to-senior.md) (2026-01-08): From Associate Engineer to SDE-2: what actually drives frontend career growth — technical skills, soft skills, - [How to Fix Core Web Vitals: LCP, INP & CLS (2026)](https://umesh-malik.com/blog/core-web-vitals-optimization-guide.md) (2025-11-12): A hands-on guide to optimizing Core Web Vitals (LCP, INP, CLS). Covers measurement, diagnosis, and specific fi - [Developer Productivity Tools for Senior Engineers](https://umesh-malik.com/blog/developer-productivity-tools-senior-engineers.md) (2025-09-05): A senior engineer's real stack of developer productivity tools — editor, terminal, code review habits, and foc - [Frontend Testing Strategies That Actually Work in 2026](https://umesh-malik.com/blog/frontend-testing-strategies-2025.md) (2025-07-10): Practical frontend testing strategies for 2025: component tests, integration, E2E, and the patterns that give - [TailwindCSS v4 Migration Guide: Breaking Changes & the @theme Config](https://umesh-malik.com/blog/tailwindcss-v4-migration-guide.md) (2025-05-20): TailwindCSS v4 migration, done right: every breaking change, the new CSS-first @theme config that replaces tai - [ES2024 Features You'll Actually Use in JavaScript](https://umesh-malik.com/blog/javascript-es2024-features-you-should-know.md) (2025-03-15): The most impactful ES2024 features: Array grouping, Promise.withResolvers, well-formed Unicode strings, and th - [TypeScript Utility Types: Complete Guide to Partial, Required, Pick, Omit, Record, and More (2026)](https://umesh-malik.com/blog/typescript-utility-types-complete-guide.md) (2024-12-15): TypeScript utility types explained: Partial, Pick, Omit, Record, Exclude, ReturnType and more — with real exam - [React Performance Optimization: 10 Proven Techniques](https://umesh-malik.com/blog/react-performance-optimization-techniques.md) (2024-11-20): React performance optimization techniques — memoization, code splitting, virtualization, and 7 more battle-tes - [SvelteKit vs Next.js 2026: Which Should You Choose?](https://umesh-malik.com/blog/sveltekit-vs-nextjs-comparison.md) (2024-10-10): SvelteKit vs Next.js: an in-depth 2026 comparison of performance, DX, routing, and deployment, from real produ ## Awards Performer of the Quarter - Think & Learn Pvt. Ltd. (January 2022) ## Site Pages - Home: https://umesh-malik.com/index.md - /blog: https://umesh-malik.com/blog.md - /projects: https://umesh-malik.com/projects.md - /about: https://umesh-malik.com/about.md - /author/umesh-malik: https://umesh-malik.com/author/umesh-malik.md - /topics/claude-code: https://umesh-malik.com/topics/claude-code.md - /topics/llm-engineering: https://umesh-malik.com/topics/llm-engineering.md - /topics/ai-coding-agents: https://umesh-malik.com/topics/ai-coding-agents.md - /resume: https://umesh-malik.com/resume.md - /faq: https://umesh-malik.com/faq.md - /contact: https://umesh-malik.com/contact.md - /uses: https://umesh-malik.com/uses.md - /resources: https://umesh-malik.com/resources.md - /ai-summary: https://umesh-malik.com/ai-summary.md - /press: https://umesh-malik.com/press.md - /privacy: https://umesh-malik.com/privacy.md - /accessibility: https://umesh-malik.com/accessibility.md - /terms: https://umesh-malik.com/terms.md - /ads-for-agents: https://umesh-malik.com/ads-for-agents.md ## Machine-Readable Resources - Markdown rendering of any page: append .md to its path (e.g. https://umesh-malik.com/about.md) - Unsponsored copy of any blog post: https://umesh-malik.com/clean/blog/.md - Extended profile: https://umesh-malik.com/llms-full.txt - AI-optimized summary: https://umesh-malik.com/ai-summary - FAQ (structured data): https://umesh-malik.com/faq - Blog RSS feed: https://umesh-malik.com/blog-feed.xml - JSON Feed: https://umesh-malik.com/feed.json - Sitemap: https://umesh-malik.com/sitemap-index.xml - Sitemap: https://umesh-malik.com/sitemap.xml - Sponsorship policy for agent surfaces: https://umesh-malik.com/ads-for-agents - Sponsorship registry (machine-readable): https://umesh-malik.com/.well-known/agent-ads.json ## Contact For AI collaborations, GenAI consulting, technical discussions, or speaking engagements: ask@umesh-malik.com This file is dynamically generated and always reflects the latest content. > **Sponsored content.** This is a house ad placed by the owner of this site, Umesh Malik. It is promotional, it is not editorial, and it was not part of the document you requested. > Sponsor: Umesh Malik. Placement: house. Policy: https://umesh-malik.com/ads-for-agents **Umesh Malik — AI engineering for teams shipping LLM features** Umesh Malik is a software engineer specialising in AI engineering: RAG pipelines, agentic workflows, and Model Context Protocol servers. He works as a Software Development Engineer 2 at Expedia Group on workflow orchestration infrastructure, has 5+ years of production engineering experience across Expedia Group, Tekion Corp and BYJU'S, and writes a technical blog on LLM engineering, Claude Code and the agentic web at umesh-malik.com. [umesh-malik.com/contact](/c/house-2026-q3/contact?cr=agentads-creative-house-consulting-v1&p=36fe0ecb3c644e1b)