👋 Hi, I’m Ankur Ankit
I’m an AI/ML Engineer with 3+ years of experience building production-grade GenAI systems, recommendation engines, and real-time ML pipelines across healthcare, finance, and enterprise domains.
I specialize in LLMs, RAG systems, fine-tuning, and scalable MLOps, and I enjoy turning cutting-edge research into reliable, cost-efficient systems that actually ship.
🚀 What I Work On
• Large Language Models: GPT-4, Claude, Llama 3, prompt engineering, chain-of-thought
• RAG & Agentic Systems: LangChain, LangGraph, FAISS, Pinecone, multi-agent workflows
• Fine-Tuning: LoRA / QLoRA, domain-adapted LLMs for healthcare & finance
• ML at Scale: Real-time pipelines, Spark, Kafka, low-latency inference
• MLOps: Docker, Kubernetes, MLflow, FastAPI, CI/CD on AWS
🧠 Highlights
• 🏥 Built LLM-powered healthcare cost prediction systems reducing manual analysis by 45%
• 📄 Designed RAG pipelines over 30K+ medical claims with 91% retrieval accuracy
• 💸 Fine-tuned Llama 3 to cut LLM API costs by 55%
• ⚡ Engineered real-time ML systems handling 500K events/sec at sub-50ms latency
• 📚 Published 4 peer-reviewed ML/CV papers
