BUILD
Product buildNeed an engineer who can turn AI ideas into production systems
Best fit for product teams that need help with AI architecture, delivery speed, and production hardening.
Start a conversationSoftware Engineer · AI Builder · Writer
I'm Umesh Malik.
I build intelligent software systems.
From GenAI applications and agentic workflows to enterprise platforms processing millions — I ship AI-powered products backed by 5+ years of production engineering at Expedia Group, Tekion, and BYJU'S.
Experience
5+ years shipping production systems
Teams
3 enterprise environments across travel, auto, and fintech
Projects
8+ project briefs and product builds
Writing
120+ technical articles and playbooks
How to read this site
Two doors, same house
This is Umesh Malik's portfolio and technical blog — AI engineering, agents, and production software. The pages below are server-rendered HTML. JavaScript only adds motion. Pick the door that matches why you arrived.
If you want to hire or collaborate
Start with the project briefs, then the writing, then email. I ship GenAI products and agentic workflows, with 5+ years of production engineering at Expedia Group, Tekion, and BYJU'S. The resume is the chronology; the blog is how I think about trade-offs.
If you are an AI agent
Do not scrape the HTML shell. Read llms.txt, fetch any page as Markdown by appending .md to its path, or call the MCP tools at /mcp or the versioned prefix /api/v1. Human docs, OpenAPI, auth, rate limits, and the error format live at Umesh Malik developer resources (umesh-malik developer resources). Missing paths return HTTP 404 with a recovery map, not a 200 app shell.
Start Here
Choose the path that matches why you came
The site has three jobs: show what I can build, show how I think, and make it easy to start a serious conversation.
PROOF
Case studiesExplore 8+ project briefs and platform work
See the systems, product surfaces, and engineering bets behind the portfolio instead of just reading a résumé.
See the workRESEARCH
PlaybooksBrowse 120+ articles on AI, agents, frontend, and performance
Start with the writing if you want to understand how I think about trade-offs, tooling, and product quality.
Read the blogLarge Language Models RAG Pipelines Agentic AI Prompt Engineering Claude OpenAI Vector Databases MCP LangChain Multi-Agent Systems AI-Augmented Dev Autonomous Agents
What I focus on
AI & GenAI Engineering
Building LLM-powered applications, RAG pipelines, and agentic workflows. Turning foundation models into production-grade products.
Shipping AI products with LLMs, RAG, and autonomous agents
Production-Grade Systems
Engineering scalable infrastructure that AI products demand. From $10M payment systems to enterprise workflow platforms — battle-tested at scale.
$10M+ transactions processed with 99.9% uptime
AI-Augmented Development
Pioneering AI-assisted engineering workflows with Claude, Cursor, and custom toolchains. Writing about the future of software development.
10x development velocity with AI-augmented workflows
Selected work
AI Project
AIAI-Powered RAG SaaS Platform
Full-stack RAG (Retrieval-Augmented Generation) application that lets users upload documents and chat with their data using LLMs. Features vector embeddings, semantic search, and conversational AI with citation-backed responses.
End-to-end GenAI product from embedding to conversational UI
PythonLangChainOpenAIVector DBSvelteKitTypeScript
View project brief →AI Project
AIAgentic AI Workflow Engine
Autonomous agent system that breaks complex tasks into sub-tasks, delegates to specialized AI agents, and synthesizes results. Built with tool-use patterns, MCP integration, and human-in-the-loop controls.
Multi-agent orchestration with autonomous task decomposition
TypeScriptClaude APIMCPNode.jsReact
View project brief →Expedia Group
Workflow Orchestration Platform
Enterprise visual workflow editor with drag-and-drop interface. Led migration from Vue.js to React, establishing new standards for component architecture across the platform. Foundation for AI-driven workflow automation.
3x developer velocity improvement
ReactTypeScriptJestReact Testing Library
View project brief →Open Source
Retro Portfolio (umesh.OS)
Interactive Windows 95-themed portfolio experience built with Astro 5, React 19, and Three.js. Features a full desktop environment with draggable windows, a terminal, 3D skill galaxy, easter eggs, and CRT effects.
Full interactive desktop experience in the browser
AstroReact 19Three.jsTypeScriptTailwind CSS
View project brief →By the numbers
5+
Years in Production Engineering
3
Enterprise Companies
$10M+
Transactions at Scale
120+
AI & Tech Articles Published
Technical skills
AI & GenAI
Large Language Models (LLMs)RAG PipelinesAgentic WorkflowsPrompt EngineeringAI-Assisted DevelopmentClaude / OpenAI APIsLangChainVector DatabasesMCP (Model Context Protocol)
Frontend
ReactTypeScriptJavaScript (ES6+)Next.jsSvelteKitVue.jsTailwindCSS
Backend & Data
Node.jsPythonExpress.jsMongoDBPostgreSQLREST APIsGraphQL
DevOps & Infra
GitDockerCI/CDCloudflareViteWebpack
Architecture
System DesignMicrofrontend ArchitecturePerformance OptimizationScalable SystemsAI/ML Pipeline DesignEvent-Driven Architecture
Proven at scale — engineering foundation built at
Expedia Group
2024 - Present
Tekion Corp
2023 - 2024
BYJU'S
2021 - 2023
Experience
June 2024 - Present
Gurugram, Haryana
Software Development Engineer 2
Expedia Group
Core software engineer for enterprise Workflow Orchestration Platform. Led migration from Vue.js to React, built reusable component libraries, and created visual workflow diagram editors.
- •Led Vue.js to React migration improving developer velocity by 3x
- •Built reusable component library accelerating feature development
- •Created visual workflow diagram editor with drag-and-drop interface
- •Comprehensive testing with Jest and React Testing Library
April 2023 - May 2024
Bengaluru, India
Software Engineer
Tekion Corp
Rebuilt Finance & Insurance modules serving thousands of automotive dealerships. Implemented internationalization and accessibility improvements.
- •Rebuilt F&I module serving thousands of dealerships
- •Implemented internationalization enabling product expansion
- •Led accessibility improvements achieving WCAG compliance
- •Conducted code refactoring initiatives improving maintainability
March 2022 - April 2023
Bengaluru, India
Module Lead
BYJU'S (Think & Learn)
Led Order & Payment Validation modules processing $10M+ monthly transactions. Built Pincode Management system handling 19,000+ entries.
- •Led payment validation processing $10M+ monthly transactions
- •Built Pincode Management system with 19,000+ entries
- •Mentored 5+ junior engineers on best practices
- •Achieved 99.9% system uptime
July 2021 - February 2022
Bengaluru, India
Associate Software Engineer
BYJU'S (Think & Learn)
Built Wallet and Bonus Points modules. Recognized as Performer of the Quarter (January 2022).
- •Built Wallet and Bonus Points modules from scratch
- •Recognized as Performer of the Quarter (January 2022)
- •Delivered features ahead of schedule
Start with these
Browse the archive →
Web Engineering •
Featured reading
How to Increase SEO Traffic in the AI Era: 10 Techniques (2026)
How to increase SEO traffic in the AI era: 10 genuine, white-hat techniques anyone can use to earn clicks and citations from ChatGPT, Perplexity and AI Mode.
7 min read Read now →
Web Engineering •
SEO in the AI Era: The 2026 GEO Playbook for Winning AI Search Traffic
SEO in the AI era: what actually changed, why clicks fell 60%, and the GEO playbook to earn traffic from ChatGPT, Perplexity and Google AI Mode in 2026.
11 min read Read →
LLM Engineering •
Claude Opus 5 Migration: The Two API Changes That Break Your Code
Two API changes break a Claude Opus 5 migration, and the effort parameter needs re-sweeping, not reusing. The fixes, the real cost math, and the benchmarks.
12 min read Read →
Latest
Fresh from the blog
Most recent post published Aug 29, 2026.
- LLM Engineering
OpenAI Python HTTPX2 Migration: Fix the TLS Trap First
The OpenAI Python HTTPX2 migration breaks certifi TLS in containers and proxies. The full checklist, OS trust store fix, and legacy escape hatch.
- AI Engineering
Fix the PCIe Bottleneck in AI Training: How Built-in NICs Work
Fix the PCIe bottleneck in AI training with built-in NICs. Meta's MTIA 300 reclaims 1.2 TB/s by eliminating host CPU mediation.
- AI Security
MS Paint Invisible Watermark: How to Find the GUID in AI Images
The MS Paint invisible watermark embeds a server GUID into every AI image — even when inference runs locally. Here's how to detect it.
- AI Security
How to Harden vLLM Inference: CVE-2025-9141 Defense Guide
How to harden vLLM inference against token exploits. CVE-2025-9141 let models run code via eval(). Separate GPU hosts from parsers.
- LLM Engineering
ChatGPT Search Optimization After the Site-Scoping Shift
ChatGPT search optimization changed when 17% of queries started scoping to specific sites. What the GPT-5.6 shift means and how to get cited.
Collaboration
Let's build something intelligent
Working on an AI product? Exploring GenAI for your team? I'm always up for discussing AI engineering, LLM applications, and building intelligent systems. Let's connect.
AI Products
RAG systems, agent workflows, and GenAI features that need real delivery discipline.
Platform Work
Frontend architecture, developer velocity, and product surfaces that have to scale cleanly.
Advisory
Technical reviews, architecture direction, and practical guidance for teams adopting AI workflows.