• Design, build, and operate LLM-powered systems used in production, from initial design through deployment and iterations • Build scalable agentic AI automation solutions, selecting appropriate patterns (reasoning, memory, agent frameworks, MCP’s, workflow orchestration, fine-tuning) based on business requirements • Implement GenAI patterns such as RAG, tool/function calling, and multi-step workflows, selecting approaches based on accuracy, reliability and cost • Develop and maintain data ingestion and retrieval pipelines, especially for unstructured or semi-structured documents • Fine-tune and adapt open-source or commercial LLMs for domain-specific tasks when appropriate • Set quality, evaluation, and reliability standards for GenAI systems, including testing, monitoring, observability, and failure handling • Make system-level tradeoffs across model choice, latency, cost, accuracy, and operational complexity, and guide teams through those decisions • Deploy and monitor GenAI services on AWS, optimizing for latency, cost, and system stability • Collaborate with product managers and domain experts to translate requirements into technical solutions • Establish golden paths (templates, examples, docs) and contribute to shared GenAI libraries, patterns, and best practices used by other engineers • Provide technical guidance and mentorship to mid-level engineers