Jobs

Vals AI is seeking a strong Evaluations Engineer to own and maintain their LLM leaderboards, which are crucial for evaluating model performance across various real-world tasks. This role involves testing new models against benchmarks, analyzing error modes, and collaborating with communications to release results. The ideal candidate will have strong engineering fundamentals, Python expertise, familiarity with LLMs, and a willingness to work intensely during model releases. Join a fast-paced team building the standard for LLM evaluation, with work featured by major publications.