Own the evaluation, selection, optimization, and production deployment of large language models powering legal and medical document workflows. Build EvalOps and monitoring frameworks, benchmark model quality, cost, speed, and resilience, manage model transitions, optimize RAG and orchestration pipelines, and reduce hallucinations. Partner with product and go-to-market stakeholders while independently implementing changes across staging and production.

Own evaluation, selection, and continuous optimization of LLMs and AI pipelines for legal and medical document tasks. Build Eval frameworks, implement RAG and embedding-based systems, integrate and transition models into production on cloud, monitor performance and cost, and document runbooks. Collaborate cross-functionally and take end-to-end ownership of deployments and validation.