Design, build, and operationalize production LLM and generative AI applications using Claude, GPT, or Gemini, including prompt engineering, RAG implementations, tool/function calling, and secure endpoints. Implement ML data pipelines, feature engineering/serving, and real-time inference services with attention to latency, cost, and reliability.… Lead security, compliance, and governance efforts across LLM/MLOps platforms, including PII handling, access controls, and monitoring. Collaborate across teams on design reviews, deployment readiness, and incident response while managing enterprise integrations via REST, GraphQL, microservices, and event-driven architecture.
San DiegoLast seen today