Kernel Engineer
Cerebras Systems, Inc.Visit Cerebras Systems, Inc. website
Cerebras builds wafer-scale AI computing systems and a cloud inference platform for training, fine-tuning, and serving AI models.
Sunnyvale, California, United States
About Cerebras Systems, Inc.
Cerebras Systems is an AI-infrastructure company founded in 2015. It sells rack-scale wafer-scale computing systems and provides cloud-based, API-accessible AI inference alongside on-premises deployments.
Skills
About the Role
You will design, implement, debug, optimize, and validate low-level kernels for machine learning and HPC workloads. You will develop parallel algorithms, analyze performance, build testing methods, and work with hardware architects on future instruction sets and systems.
Requirements
- Understanding of hardware architecture
- C++ and Python programming skills
- Knowledge of library and API development practices
- Debugging skills for complex software stacks
Responsibilities
- Develop specifications for machine learning and linear algebra kernels
- Develop and debug optimized kernel libraries in assembly and CSL
- Implement algorithms for Cerebras hardware
- Use mathematical analysis to measure performance and inform design decisions
- Develop unit and system testing methodologies for kernel libraries
- Study machine learning trends and evolve kernel-library architecture
- Work with chip and system architects to optimize instruction sets, microarchitecture, and I/O