Join a platform team building production GenAI capabilities used across regions. You will help deliver platform utilities (model hosting, inference, evaluation, memory management) and ship impactful GenAI use cases using our internal tooling on Databricks and AWS.
Key responsibilities
- Build and improve GenAI platform components: serving/inference paths, evaluation pipelines, and memory management utilities.
- Deliver priority GenAI use cases with internal platform tooling; iterate with users and measure outcomes.
- Write production-quality Python code with tests, reviews, and documentation.
- Work in Databricks for development and pipelines; integrate with AWS services and (where needed) EKS.
- Improve reliability, cost, and latency through profiling, observability, and pragmatic optimization.