Design, build, and operate scalable backend and ML infrastructure for search, retrieval, ranking, and recommendation. Own ML pipelines (Vertex AI Pipelines), vector generation/storage, model serving (KServe), REST/GraphQL APIs (FastAPI), observability, and data pipelines (Beam/Airflow). Collaborate with data science, product, and platform teams to deliver production ML features, debug production issues, and maintain documentation and engineering standards.