srinu karneedi

I’m an AI/ML Engineer with 3+ years at TCS building production GenAI systems—RAG pipelines, fine-tuning (LoRA/QLoRA), and multi-agent workflows. I own the full path from model prototype to production by combining LLM stack depth with platform engineering fundamentals.

I’ve designed and deployed production RAG pipelines for enterprise document intelligence, improving retrieval accuracy ~25% using hybrid search (BM25 + dense vector) with cross-encoder reranking. I built multi-agent workflows with LangGraph and CrewAI, added LLM evaluation pipelines (RAGAS + custom LLM-as-judge), and set up MLflow for experiment tracking, model registry, and automated regression testing.

On the platform side, I’ve integrated vLLM for self-hosted inference, optimized embeddings pipelines to cut ingestion latency by 40%, and reduced end-to-end RAG response latency 30–40% using Redis semantic caching and async execution. I also deploy and operate FastAPI-based services on AWS EKS with Terraform IaC, CI/CD, and observability—so performance, reliability, and governance are built in from day one.