We’re looking for a Founding AI Engineer to help build BENCH
BENCH helps companies building with AI continuously measure and improve quality while reducing model costs. We’re building the evaluation layer we wished we had while running 84 AI agents in production at our previous startup.
You’ll work directly with the founders across LLM evaluations, agents, synthetic data, benchmarking, model optimization and core product infrastructure.
Early stage. High ownership. Lots to build.