Agentic Data Scientist: Benchmarking & Evaluation

jobr.pro based in Sunnyvale, California is seeking a Research Scientist focused on agentic language models. The ideal candidate will manage a complete data pipeline, ensuring high-quality results and rigorous evaluations. Responsibilities include developing metrics for agentic performance and collaborating with product teams to translate capability goals into measurable artifacts.
Candidates should have a strong foundation in Python and PyTorch, preferably with experience in reinforcement learning environments and data curation.

#J-18808-Ljbffr