- Design, build, and optimize ML pipelines for context retrieval, action detection, and output generation
- Implement and iterate on RAG systems, ranking models, and prompt engineering to improve quality
- Build comprehensive evals and monitoring to measure and improve ML system performance
- Investigate alternative models and fine tuning approaches for our heavy background processing workloads, implementing better systems to increase quality while improving cost efficiency
- Collaborate with Backend and Product Engineering to ship AI powered features
- Contribute to ML infrastructure decisions and best practices across the engineering org
- Stay current on LLM advances, retrieval techniques, and ML tooling; bring insights back to the team
Profile
We’re looking for someone who is interested in building the AI user experience for the future. We punch above our weight so we value extreme ownership, accountability, and proactiveness. The ideal candidate is a master craftsman who enjoys building great products with LLMs at scale.