# Ishan Avasthi

> AI Engineer and CS undergrad at BITS Pilani, India, open to AI engineering roles. I build LLM-powered systems, agentic workflows, and developer tools.

I'm a CS undergrad at BITS Pilani working on AI engineering. I build the layer between raw language models and working products: agent pipelines, RAG systems, and the observability and evals that make them reliable enough to ship.

In practice that means pipelines that retrieve the right context, agents that take actions, and tooling that makes the whole thing reliable. I care about testing things properly, making systems easy to work with, and shipping stuff that holds up in the real world.

- **Role:** AI Engineer
- **Based in / studying at:** IND · BITS Pilani
- **Status:** open to AI engineering roles
- **Email:** hello@ishanavasthi.in
- **Website:** https://ishanavasthi.in
- **GitHub:** https://github.com/ishanavasthi
- **LinkedIn:** https://www.linkedin.com/in/ishanavasthi

## Skills

- **Agents & LLM Systems** (the core focus): Multi-agent pipelines, MCP, Tool calling, Human approval gates, Claude API · Agent SDK, OpenAI · Azure OpenAI, Gemini, Groq, LangGraph, LangChain, Voice agents · LiveKit, RAG · pgvector · ChromaDB — 15 projects
- **Evals & Reliability** (what makes agents shippable): Agent evals, LLM-as-judge, OpenTelemetry tracing, Golden sets · replay cassettes, LangSmith, RL environments · OpenEnv, CI regression gates, Deterministic guardrails, Prompt-injection defense, SigNoz / ClickHouse — 10 projects
- **Languages** (daily drivers first): Python, TypeScript, Go, JavaScript, Java, SQL, C# — 15 Python, 13 TS
- **Backend & Infra**: FastAPI, Node / Express, Hono, Spring Boot, Postgres · Drizzle · Prisma, Supabase, MongoDB, Job queues · outbox, Docker, GitHub Actions, AWS · Azure, asyncio / TCP — 15 projects
- **Frontend**: Next.js, React, Tailwind CSS, shadcn/ui, Zustand · TanStack Query, React Native, Chrome Extensions · MV3 — 9 projects

## Projects (34)

- **Agents & LLM Systems** (12): Multi-agent pipelines, tool-calling agents, and the observability around them.
- **RAG & Document AI** (3): Retrieval pipelines over documents people actually need to read.
- **RL Environments & Evals** (2): OpenEnv-compliant environments for training and grading agents.
- **Developer Tools** (4): Small, sharp utilities built to remove a specific daily friction.
- **Full-Stack & Web** (4): Product-shaped web apps, end to end.
- **Foundations** (9): Earlier work — Spring Boot services, low-level design, Java, and data analysis.

Full list: https://ishanavasthi.in/projects.md

## Writing

- [Your agent got 3x more expensive and every test still passed](https://ishanavasthi.in/blog/catching-agent-regressions-in-ci.md) (2026-07-27)
