About Hemang Baldha
AI engineer in Ahmedabad, Gujarat, building retrieval, agent and voice systems that run in production.
I am an AI engineer with two years of experience building systems that make it to production, not just notebooks. The unglamorous parts are where I spend my time: retrieval quality, latency budgets, evals and clean data.
Day to day that is production RAG, LLM integrations and agent workflows, and voice and audio pipelines, with fine-tuning and computer vision alongside. Lately: a multi-tenant RAG platform, an NL-SQL engine that queries 20+ databases, and a LoRA-fine-tuned vision-language model watching real warehouses.
Away from work I won first place at two hackathons, and I have taught more than 500 students as a teaching assistant at Darshan University. I like leading technical projects and bridging AI research with applications people actually use. I am based in Ahmedabad, India.
Recently working with
Python, PyTorch, LangChain and LangGraph, Hugging Face, Whisper and TTS, OpenCV, Pinecone and pgvector, FastAPI, Next.js and React, TypeScript, PostgreSQL, AWS and Docker.
What I work with
An honest split of where I am deep and where I am still learning, after two years of building AI systems.
Deep
Where I have shipped production systems and know the failure modes.
Retrieval & dataRAG & Retrieval
Hybrid search & reranking; Pinecone, pgvector, FAISS; Chunking strategy & RAG evals; Citation-grounded answers.
Models & agentsLLM Integration & Agents
OpenAI, Claude, open-weights; Function calling & tool use; LangChain, LangGraph workflows; Streaming, guardrails, cost tuning.
Voice & audioVoice & Audio AI
ASR / TTS pipelines (Whisper+); Audio processing for voice models; Real-time streaming audio; VAD & speaker diarization.
Web & toolsFull-Stack & Serving
FastAPI, Node services; Next.js, React frontends; Postgres + pgvector; Docker, AWS deploys.
Working knowledge
Real project work, but less miles. I am still building depth here.
Models & agentsFine-tuning
LoRA, QLoRA, PEFT; Dataset curation & cleaning; Instruction tuning; Evaluation loops.
Models & agentsComputer Vision
Detection & classification; OCR & document AI; OpenCV pipelines; Image preprocessing.