Manager Kernel Software
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
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will lead engineers developing, optimizing, debugging, and validating low-level kernels for machine learning and HPC workloads. You will set technical direction, drive execution, develop parallel algorithms, analyze performance, evolve kernel architecture, and work with hardware architects.
Requirements
- Experience leading technical teams and mentoring engineers
- Understanding of hardware architecture
- C++ and Python proficiency
- Low-level systems programming experience
- Knowledge of library and API development practices
- Performance optimization skills
- Debugging skills for complex layered software stacks
Responsibilities
- Lead kernel-development technical teams
- Set technical direction and drive execution
- Develop specifications for machine learning and linear algebra kernels
- Develop and debug optimized kernel libraries in assembly and CSL
- Use mathematical analysis to measure performance and inform design decisions
- Develop unit and system testing methodologies for kernel libraries
- Evolve kernel-library architecture for neural-network workloads
- Work with chip and system architects to optimize future systems