Design and ship LLM-powered features including AI assistants and automated workflows — from idea to production.
Architect and implement multi-step agent systems, integrating external tools, APIs, and retrieval pipelines to solve complex tasks reliably.
Build, maintain, and improve data pipelines and orchestration flows using Prefect, ensuring reliability, observability, and on-time delivery of data to AI systems.
Own the migration of ML prototypes into robust production services, defining clear SLOs, monitoring strategies, and rollback plans.
Implement security, governance, and compliance controls to ensure responsible AI usage across all deployed systems.
Partner with Product, Design, and UX teams to run structured evaluations, gather user feedback, and drive continuous quality improvements.
Champion engineering best practices — code quality, observability, documentation — across the AI stack.
Requirements
Proven experience in Software Engineering or Machine Learning with hands-on work building and shipping LLM-powered applications in production.
Deep expertise in Python and TypeScript; strong command of API design, vector search, and embedding pipelines.
Experience with prompt engineering, evaluation frameworks, and tooling for systematic LLM quality measurement.
Familiarity with agent frameworks (e.g. Pydantic AI) and tool/function-calling integration patterns.
Hands-on experience building and operating data pipelines — ideally with Prefect or a comparable orchestration tool (Airflow, Dagster).
Solid working knowledge of AWS services used in data platforms: S3, EC2, IAM, CloudWatch.
Excellent problem-solving skills and a track record of navigating ambiguous, fast-moving environments.
Clear communicator — able to translate complex technical concepts for non-technical stakeholders and build shared understanding across disciplines.