Engineering Evaluation Platform Developer

We are a remote-first team across Europe and North America, focused on building a scalable self-serve evaluation platform for AI models. Your role involves designing and implementing a Python framework for benchmarking, building distributed evaluation pipelines, and collaborating with research and product teams to improve tooling. The team values high-quality engineering, reliability, and collaboration with ML engineers and researchers. Benefits include fully remote work, flexible hours, 37 days of vacation, health insurance allowance, company equipment, and team get-togethers.