Cerebras
CoDesign & NextGen Performance Engineer
- Confirmed live in the last 24 hours
- No salary listed
- Mid level
- Full-time
- Remote · Sunnyvale, CA
- 3+ yrs exp
- Added 2 months ago
About this role
Cerebras Systems is seeking a CoDesign & NextGen Performance Engineer to optimize AI model performance on their unique wafer-scale hardware. This role involves analyzing bottlenecks, improving computational efficiency, and contributing to the design of future AI architectures and software. You'll work closely with leading AI labs and enterprises to push the boundaries of AI performance.
What you'll do
- Optimize performance on new Cerebras WSE generations.
- Build performance models at the kernel and end-to-end levels.
- Optimize and debug kernel microcode and compiler algorithms.
- Debug and understand runtime performance on the system and cluster.
- Develop tools for visualizing performance data from the Wafer Scale Engine and compute cluster.
What they're looking for
- Computer Architecture
- Deep Learning/LLM Math
- Analytical and Problem-Solving
- CPU/GPU Simulators
- Performance Profiling
- Python
Benefits
- Work on a breakthrough AI platform
- Startup vitality with job stability
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Cerebras
Likely interview questions
- Describe a time you identified and resolved a performance bottleneck in a complex system.
- Explain your experience with performance profiling tools and techniques.