Machine Learning Engineer with 9+ years' experience in deep learning, reinforcement learning, and large language model (LLM) deployments at scale. Skilled in delivering production-ready models and cloud architectures using Python, TensorFlow, PyTorch, Docker, and Kubernetes. Recently focused on LLM-powered applications, including scalable inference pipelines and integrations with frameworks like LangChain and retrieval-augmented generation (RAG) backed by vector stores. Experienced across startups and enterprise settings—from prototype to production.