Cerebras
ML Systems Performance Engineer
United States and Canada · Full-time · Posted Jan 21, 2026
- Experience
- 3+ years in a relevant domain (Computer Architecture, CPU/GPU Performance, Kernel Optimization, HPC).
- Education
- Bachelor’s / Master’s / PhD in Electrical Engineering or Computer Science.
About the job
Build performance models, optimize kernels and compiler algorithms, analyze system and cluster runtime performance, and develop tools to improve ML inference on Cerebras hardware.
What you'll do
- Model kernel-level and end-to-end performance for state-of-the-art and customer ML models.
- Debug and optimize kernel microcode and compiler algorithms to improve inference speed, throughput, and compute utilization.
- Analyze runtime performance and develop tools to visualize performance data from the Wafer Scale Engine and compute cluster.
What they ask for
- Bachelor’s, Master’s, or PhD in Electrical Engineering or Computer Science.
- Strong background in computer architecture and understanding of low-level deep learning / LLM math.
- Experience with CPU/GPU simulators and performance profiling and debugging on a system pipeline.
- Comfort with C++ and Python.
Tools
C++, Python, Cerebras WSE, Wafer Scale Engine
AI focus
Improve ML model inference speed, throughput, and compute utilization through performance modeling, kernel and compiler optimization, runtime analysis, and diagnostics tooling.
Model-written summary · the original posting is authoritative