Build and deploy production-ready Generative AI and LLM applications, including RAG systems, chatbots, copilots, intelligent automation, and agentic workflows. Develop Python backend services, integrate LLM APIs, optimize model quality and performance, implement evaluation and guardrails, and troubleshoot deployed systems. Collaborate with engineering, product, operations, and business teams in a globally distributed environment while translating AI capabilities into scalable production solutions.

Build and maintain Python backend services and internal tools for AI/LLM applications. Integrate LLM APIs, design scalable REST APIs and async workflows, handle prompt management and model routing, monitor performance, debug distributed systems, automate data workflows, and collaborate to productionize AI features with emphasis on scalability, reliability, and safety.

Apply expert investment research and capital markets knowledge to evaluate AI-generated financial analyses, validate models and valuations, identify errors, create and refine prompts and benchmark datasets, and provide actionable feedback to improve LLM performance while meeting quality and turnaround expectations.