Cerebras
AI Engineer, Model Quality and Performance
Sunnyvale, CA · On-site · Full-time · Posted May 15, 2026
About the job
Own model quality and performance for Cerebras inference offerings by building AI-driven evaluation, benchmarking, and product-quality systems.
What you'll do
- Design and curate model evaluation suites, using AI agents to generate and refine test cases.
- Build customer-specific evaluations and automate their execution, performance forecasting, and benchmarking.
- Create tooling that presents model quality and performance data in a unified view.
What they ask for
- Experience building and shipping AI-agent systems, using Claude or an equivalent.
- Strong math and statistics background.
- Comfort with Docker, Git, and standard automation tooling.
- Experience designing tooling used by non-engineers.
Nice to have
- Performance-tuning experience on custom silicon, GPUs, or FPGAs.
- Experience with evals for agentic, coding, long-context, or multimodal use cases, or familiarity with open-source eval frameworks.
Tools
Claude, Docker, Git, EvalScope, lm-eval-harness
AI focus
Use AI agents to create customer-specific evaluations, mine workload trajectories, automate release qualification, and support performance forecasting and benchmarking.
Model-written summary · the original posting is authoritative