Jayaram Sivalanka Venkata

AI Engineer with 4 years of experience designing and deploying production-ready Generative AI applications using Python, AWS Bedrock, Claude LLMs, Retrieval-Augmented Generation (RAG), and NLP. Experienced in building enterprise AI assistants, Bedrock Knowledge Base-integrated RAG systems, multi-agent workflows using LangGraph, and scalable backend services with FastAPI. Proficient in LangChain, Qdrant, PostgreSQL, Docker, Kubernetes, and AWS cloud services, with expertise in prompt engineering, semantic search, document ingestion, chunking strategies, embedding pipelines, AI agent orchestration, and fine-tuning Small Language Models (SLMs). Strong software engineering background with experience delivering secure, scalable, and production-grade AI solutions through modern DevOps and CI/CD practices.