Narayana Murthy

GenAI / LLM Platform Engineer with 7+ years of hands-on experience building, scaling, and operating production-grade AI systems. Specialized in LLM-powered platforms, agentic workflows, and retrieval-augmented generation (RAG) using LangChain, LangGraph, Transformers, and custom multi-agent architectures. Deep expertise in LLM fine-tuning, prompt engineering, evaluation, and inference optimization across models such as GPT-4 and T5. Proven experience designing high-throughput, low-latency LLM pipelines, including embeddings, vector search, context orchestration, and hallucination mitigation. Strong background in AI platform engineering and MLOps, with hands-on delivery using Python, Docker, Kubernetes, and AWS SageMaker. Built CI/CD pipelines for model lifecycle management, automated validation, monitoring, drift detection, and cost optimization at scale. Experienced in building secure, distributed GenAI platforms, integrating external APIs, vector databases, and agent-to-agent communication for enterprise use cases across healthcare, finance, and e-commerce. Passionate about turning cutting-edge GenAI research into reliable, scalable, and observable production systems.