Description
Cerebras Systems is hiring an AI Evaluation Engineer to own model quality and performance for its inference offerings. The role uses AI agents to design and automate evaluation suites, mine customer workload trajectories, build performance datasets and benchmarks, forecast production workloads, and create product-quality quality-and-performance tooling. Candidates should have experience building AI agents, a strong math and statistics background, familiarity with Docker, Git, and CI, and preferably experience with custom silicon, GPUs, FPGAs, agentic or long-context use cases, and open-source evaluation frameworks.
