AI Engineer

building production AI agents
making LLMs reliable at scale

reasoning chains • RAG pipelines • evals • observability • guardrails
feedback loops • structured outputs • tool calling • Text-to-SQL

LangChain • LangGraph • RAG • GraphRAG • Prompt Engineering • Context Engineering
Tool Calling • Structured Outputs • LLM Evals • Langfuse • Observability • Feedback Loops
Hugging Face • PyTorch • Agentic Systems • Text-to-SQL • LLMOps

FastAPI • NestJS • Node.js • Golang • Prisma • PostgreSQL • MongoDB • TypeScript

React • Next.js • Tailwind

Docker • AWS • GitHub Actions • Linux • Git