AI Inference Quality Engineer: Scale-Ready Model Performance
Cerebras
Sunnyvale (CA)
On-site
USD 120,000 - 160,000
Full time
14 days+
Get more replies from employers
Send a job-specific resume in minutes.
Start fresh or import an existing resume
Job summary
Cerebras is looking for an individual to own model quality and performance of inference offerings in Sunnyvale, California. This role involves designing eval suites with AI agents, building custom evaluations for clients, automating eval execution, and synthesizing quality and performance data into user-friendly views. The ideal candidate should have experience with AI agents, strong math and statistics background, and comfort with tools like Docker and Git. Cerebras is committed to diversity and creating an inclusive environment.
Qualifications
Experience shipping real systems using AI agents.
Ability to build automated eval executions end-to-end.
Familiar with performance tuning on silicon, GPUs, or FPGAs.
Responsibilities
Design eval suites with AI agents.
Build custom evals for target customers.
Automate eval execution with AI-driven pipelines.
Forecast and benchmark model performance for top customers.
Build tooling that integrates quality and performance data.
Skills
Experience building AI agents
Strong math/stats background
Comfort with Docker, Git, and the standard automation stack
Taste for tooling design
Job description
Cerebras is looking for an individual to own model quality and performance of inference offerings in Sunnyvale, California. This role involves designing eval suites with AI agents, building custom evaluations for clients, automating eval execution, and synthesizing quality and performance data into user-friendly views. The ideal candidate should have experience with AI agents, strong math and statistics background, and comfort with tools like Docker and Git. Cerebras is committed to diversity and creating an inclusive environment.