Production Engineering & LLMOps: Operationalize AI agents end-to-end — automated AI agent evaluation, guardrails, observability, cost and latency optimization, CI/CD, and Infrastructure as Code (Terraform, CloudFormation, AWS CDK). * Responsible AI & Security: Implement responsible-AI guardrails, data privacy, and security controls (Amazon Bedrock Guardrails, IAM, encryption, PII handling) and ensure compliance with relevant frameworks (e.g., ISO 27001, GDPR, EU AI Act). * Strong proficiency in Python, together with solid software engineering practices (version control, testing, code review).
more