Applied AI
- OpenAI GPT-4o
- Claude
- Gemini
- LangChain
- LlamaIndex
- RAG pipelines
- Function / tool calling
- ReAct agents
- Evals
- Prompt engineering
- Embeddings
- Whisper
Available for new opportunities
Top 10 · OpenAI Codex Hackathon
AI Engineer building agents, RAG systems and automation.
I’m Rohit Raj — a software and AI engineer based in Bengaluru, working remotely with teams anywhere. I build AI agents, RAG systems, n8n workflow automation and scalable APIs that solve real problems and hold up outside the demo. Open to full-time roles and contract work.
About
A short version of the story.
Most of my work lives in the unglamorous middle of applied AI — where a model meets a real product and almost everything that can go wrong, does. I build the layer that catches it: agents with tool use, retrieval pipelines that survive bad PDFs, and APIs that don’t fall over when something stops being a demo.
I care about taste as much as throughput. Typography, motion, and information density tell a user as much about a product as the model behind it — so I keep one foot in backend plumbing and the other in interfaces that feel quiet.
When I’m not shipping, I’m reading other people’s source code, benchmarking the latest model the internet pretends will change everything, and quietly resisting the next framework that promises to fix React.
Currently
- Building agents with FastAPI, tool-use loops & cost tracking
- RAG over messy real-world documents — chunking, evals, the works
- Treating evals like a first-class engineering discipline (because they are)
- Wiring Next.js + React Query frontends to all of the above
Interests
- LLM evals
- Vector search
- Agent frameworks
- Developer tools
- Design systems
- Low-latency UIs
Stack
The toolkit.
Chosen for boring reliability, not Twitter hype. Mostly.
Backend
- FastAPI
- Uvicorn
- Pydantic
- Node.js
- Express
- REST
- WebSockets
- Auth (JWT, OAuth)
- Background jobs
- uv
Frontend
- React 19
- Next.js
- TypeScript
- React Query
- Tailwind CSS
- shadcn/ui
- Framer Motion
- Vite
- Web Speech API
Data & Storage
- PostgreSQL
- MongoDB
- Redis
- SQL
- Pinecone
- Chroma
- Weaviate
- SQLite
Cloud & Infra
- Docker
- Vercel
- GCP Cloud Run
- AWS
- Railway
- GitHub Pages
- GitHub Actions
- CI/CD
- n8n
- Workflow automation
Languages & Tools
- Python
- TypeScript
- JavaScript
- SQL
- Bash
- Git
- VS Code
- Jupyter
- Postman
- ESLint
Work
A few things I’ve built.
A handful of projects I’d actually defend.
IELTS Coach
AI-powered IELTS Academic prep across all four modules — Listening, Reading, Writing & Speaking — with band-score feedback and live speech-to-text practice.
Research Agent
Production-ready ReAct agent with tool-use, persistent memory, cost tracking and prompt-injection defense — wrapped in a FastAPI service.
SECfiler RAG
A retrieval-augmented pipeline over SEC filings with evals, structured tests and a clean separation between ingestion, retrieval and generation.
LLM Extract
Schema-first structured extraction from unstructured text. Pydantic schemas, a tight LLM core, and a tiny CLI — built to slot into any pipeline.
Production API
A FastAPI service scaffolded the way I actually like — uv for deps, Pydantic everywhere, a real tests/ directory, clean app/test split. The boring base that lets the interesting stuff ship.
Claude AI Lab
A personal playground for prompts, tool-use patterns, and small Claude-powered agents — where ideas earn the right to become real projects.
GitHub
Still committing.
@rohhitrz
Last 12 months
Loading contribution history…
- Contributions
- — last 12 months
- Active days
- — last 12 months
- Longest streak
- — consecutive days
- Public repos
- — all time
Services
What I can help with.
Available to hire for full-time engineering roles or contract work — scoped builds or longer engagements. Remote, or in person in Bengaluru.
AI agents & assistants
Agents that call real tools, handle multi-step work, and stay inside a sensible cost and latency budget — research agents, domain assistants, extraction pipelines.
RAG & document intelligence
Retrieval over messy real-world sources: PDFs, filings, internal wikis. Chunking strategy, embeddings, a vector store sized to the problem, and evals that prove answers are grounded.
n8n & workflow automation
Automating the boring path between tools a team already pays for — n8n workflows, plus the custom nodes, webhooks and APIs to write when the built-in blocks run out.
Production APIs & backends
FastAPI and Node services with auth, background jobs, observability and deploys that survive contact with real traffic rather than only the happy path.
Common questions
Do you build AI agents for businesses?
Yes — it’s most of what I do. I build agents that use real tools and handle multi-step work, and I treat the evals that prove one actually works as seriously as the demo that makes it look good.
Can you build a RAG system over our internal documents?
That’s the other half of the work. Retrieval over messy sources — PDFs, filings, internal wikis — including chunking, embeddings, the vector store, and evaluation so you can tell whether an answer is grounded or invented.
Do you work with n8n and workflow automation?
Yes. n8n is often the honest answer when a problem is really about connecting tools a team already runs. I build n8n workflows and write the custom nodes, webhooks and APIs around them when the built-in blocks run out.
Are you available for full-time roles or contract work?
Both. I’m open to full-time engineering roles and to contract or freelance projects, from a single scoped build to a longer engagement. Email is the fastest way to reach me.
Do you work remotely?
Yes. I’m based in Bengaluru, India and work remotely with teams in other timezones. I’m also available in person for Bengaluru-based work.
What does your stack look like?
Python and TypeScript, mostly. FastAPI and Node on the backend; React and Next.js on the front; OpenAI, Claude and Gemini models; LangChain and LlamaIndex where they earn their place; Postgres, Redis and a vector store; Docker deploys on GCP, AWS or Vercel.
Contact
Let’s build something.
Open to full-time roles, contracts, and interesting collaborations. The fastest way is email.
Get in touch
I read every message. Yes, including the recruiter copy-paste ones — I just reply to the others first.
rohhit.rz@gmail.com