• Design, build, and deploy production-grade systems leveraging Large Language Models (LLMs) from providers like OpenAI, Google (Vertex AI), and Anthropic. • Develop and scale end-to-end applications for complex document understanding, focusing on textual, financial, and tabular data. This includes building sophisticated, high-precision RAG (Retrieval-Augmented Generation) systems that are battle-tested for production traffic. • Implement robust guardrails, validation layers, and monitoring to preemptively address model limitations, such as hallucinations, both in offline evaluation and online production environments. • Engineer and deploy complex, multi-step AI agents, with a focus on creating agentic workflows that are scalable, maintainable, and secure, especially when handling highly sensitive client data. • Own projects from conception to deployment, making key architectural decisions and ensuring the systems you build meet stringent requirements for latency, precision, and recall. • Build scalable ETL (Extract, Transform, Load) data pipelines to process and prepare complex datasets for AI model consumption. • Collaborate closely with product managers, software engineers, and other scientists to build tools, define metrics, and continuously improve the end-to-end quality of our AI systems. • Align your technical work with business outcomes, effectively communicating the impact and performance of the systems you build to stakeholders.