Open to full-time roles · Immediate joiner View LinkedIn →

Deepak Kumar Jha

Q: What is Deepak's primary tech stack?

Node.js and Express.js on the backend, Angular and React on the frontend, PostgreSQL/MongoDB/Redis for data, and AWS/GCP for cloud infrastructure. He also builds production AI features using OpenAI, Claude, and Gemini APIs with RAG architectures.

Q: Does Deepak work with remote and international teams?

Yes, delivering production work for clients in the US, UK, Canada, Australia, Europe, and the Middle East, with working-hour overlap for EST/PST, GMT, and APAC time zones.

Q: What kind of scale has Deepak built systems for?

His work includes backend architecture for HT Media's LiveHindustan.com, scaling it from crashing at 5M monthly users to smoothly handling 60M+.

Q: How do I get in touch or schedule a call?

Use the "Get in Touch" button on this page to open the contact form, message Deepak directly on LinkedIn, or email entr.deepakjha@gmail.com. Response time is typically within 24 hours.

Senior Full-Stack Engineer · Technical Lead

Node.js · Express · Angular · React · AWS · GCP — with Production AI: RAG, LLM Integration, Agentic Systems

I build backend systems that hold up under load — and AI systems that hold up in production.

I've delivered production-grade systems for teams across the US, UK, Canada, Australia, Europe & the Middle East. From MVP to 60M+ monthly active users — I write code that ships and scales.

Open to full-time Technical Lead roles in Delhi NCR and Dubai/UAE. Available within 15 days.

See the work Download CV

View full experience →

Immediate joiner · Response within 24 hours

▶ tech-stack

Backend

Node.js · 11 yrs Express.js · 10 yrs NestJS · 4 yrs TypeScript · 6 yrs REST APIs Microservices

Frontend

Angular v2–v17 · 10 yrs React · 8 yrs HTML5 / SCSS

Databases

PostgreSQL MongoDB Redis MySQL

Cloud & DevOps

AWS (EC2, S3, RDS, Lambda) Docker / Kubernetes CI/CD Pipelines GCP

AI Engineering

RAG (Retrieval-Augmented Generation) LLM Integration (Gemini, OpenAI, Claude APIs) Vector Embeddings & Semantic Search Self-Hosted LLM Inference (Ollama — Llama 3, Mistral) Multi-Model Routing Agentic AI Model Context Protocol (MCP) Prompt Engineering AI-Assisted Development (Claude Code, GitHub Copilot)

AI Engineering

Production AI, not prototypes

Privacy-First RAG

Retrieval-Augmented Generation on self-hosted Llama 3 and Mistral via Ollama. Built for cases where data cannot leave the client’s infrastructure — regulated finance, government, healthcare.

See the demos →

Multi-Model Routing

Routes each request between cloud LLMs (Gemini, OpenAI) and local inference based on cost, latency and data sensitivity.

See the demos →

Agentic Workflows (MCP)

Model Context Protocol agents connecting LLMs directly to databases, APIs and internal services for multi-step tool use.

See the demos →

Shipped LLM Features

Gemini-powered conversational support and AI-driven recommendations in production at SmartSitting — 3x growth in weekly applications.

See the demos →

Immediate Joiner

Want to work with me directly?

I'm looking for a full-time Technical Lead / Senior Full-Stack Engineer role. I've built backends that handle 60M+ monthly users, frontends engineers love working in, and AI integrations that actually ship.

AvailabilityImmediate · Full-time only

Work ModeHybrid / On-site (Delhi NCR) · Remote · Open to Dubai/UAE

Time ZonesIST · Overlap with US EST/PST, UK GMT, APAC

LocationsDelhi NCR, Gurugram, Noida, Bengaluru, Dubai

LevelTechnical Lead / Senior Individual Contributor

Primary StackNode.js · Express.js · Angular · React · TypeScript · AWS

View LinkedIn Profile Send me a message

What I bring to your team

✓
Immediate productivity
I read codebases fast, ask the right questions, and ship on day one.
✓
Scale-tested code
Built systems serving 60M+ monthly users. I write for performance and maintainability, not just demos.
✓
Full-stack ownership
Backend APIs, frontend SPAs, database design, cloud deployment — I can own the whole feature, not just a slice.
✓
AI-ready skills
RAG pipelines, OpenAI/Claude/Gemini integrations, and LLM-powered features — in production, not just tutorials.
✓
Cross-border delivery
Delivered production work for clients across the US, UK, UAE and Australia. Async-first communication, overlap hours guaranteed.

Trusted by teams at

HT MediaPublicis SapientRadisysNTT DATAIndegeneToppan Merrill

60M+

Monthly Users Served

Years Shipping Production Systems

Production AI

RAG · LLM · MCP

FAQ

Common Questions

Is Deepak Kumar Jha available for hire?

Yes. Deepak is an immediate joiner, available within 15 days, and is open to full-time Senior Full-Stack Engineer and Technical Lead roles in Delhi NCR and Dubai/UAE. Reach out via the contact form or LinkedIn.

What is Deepak's primary tech stack?

Does Deepak work with remote and international teams?

What kind of scale has Deepak built systems for?

How do I get in touch or schedule a call?

Still have questions? Let's talk it through.

A quick call is usually faster than a back-and-forth email — no pitch, just a straight answer on fit and availability.

Hire Me

Deepak Kumar Jha

I build backend systems that hold up under load — and AI systems that hold up in production.

▶ tech-stack

Production AI, not prototypes

Privacy-First RAG

Multi-Model Routing

Agentic Workflows (MCP)

Shipped LLM Features

Want to work with me directly?

What I bring to your team

Common Questions

Still have questions? Let's talk it through.

Want to work together?