Ansh Kumar Dev

WORK HISTORY

EDUCATION

ABOUT ANSH KUMAR DEV

AI Engineer with end-to-end expertise in designing and deploying production-grade Generative AI systems. I specialize in LLM-powered applications, vector-based semantic retrieval, and Retrieval-Augmented Generation (RAG) pipelines using OpenAI, LangChain, FAISS, and Qdrant.Skilled in architecture design, cloud infrastructure, and cost-aware engineering, I build scalable, multi-tenant platforms using AWS (S3, Lambda, ECS, RDS), Flask, Docker, and PostgreSQL. I focus on high-performance, modular systems with observability, fault tolerance, and efficient resource usage.I have a strong track record of delivering in fast-paced, sprint-driven environments, balancing rapid prototyping with stable deployment. My work includes LLM optimization, token-aware chunking, embedding pipelines, and robust backend APIs, all designed to reduce latency, improve search precision, and scale across millions of data points.Deeply invested in research and development, I continually explore new ways to enhance document intelligence, vector search, and LLM retrieval strategies for real-world impact.