AI/ML Engineer with 6 years of experience building and deploying production-grade AI systems at Goldman Sachs and across enterprise platforms, partnering closely with stakeholders to deliver reliable and scalable solutions. I specialize in large language models, retrieval-augmented generation (RAG), agentic AI, embeddings, and vector search to design enterprise copilots, knowledge assistants, and intelligent automation systems. I have a proven track record of integrating AI with observability and incident management platforms, reducing MTTR by 38% and significantly improving operational efficiency. My work includes strong hands-on experience in LLM orchestration using LangChain and LlamaIndex, prompt engineering, tool and function calling, semantic retrieval, and multi-agent workflows, along with building end-to-end machine learning pipelines for NLP, computer vision, anomaly detection, and predictive modeling using PyTorch and TensorFlow. I also design and develop FastAPI-based AI services and RESTful APIs, deploying scalable, cloud-native workloads on AWS using Docker, Kubernetes, and CI/CD pipelines, while following MLOps best practices such as model monitoring, validation, governance, and A/B testing. I focus on delivering reliable, cost-efficient AI solutions through prompt optimization, model routing, and performance tuning, consistently meeting strict production SLOs.