Staff Kernel Optimzation Engineer

Cerebras
Anywhere
Workplace: RemoteFull timeFunction: Healthcare (Clinical, Medical, Wellness)Skills: ["Debugging","Problem-solving","Analysis"]

Develop and optimize high-performance ML and HPC kernel software for Cerebras’ massively parallel processor architecture. Design and map new machine learning and linear algebra kernels to the WSE system, build and debug optimized low-level assembly and custom CSL routines, and use performance modeling to drive design decisions. Own validation by creating unit and system test methodologies, and collaborate with chip and system architects to tune instruction sets, microarchitecture, and IO.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Cerebras
Cerebras
7 months ago

Staff Kernel Optimzation Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 16 hours agoStatus: Live
Reposted: similar role first listed 2 months ago

Job Summary

Develop and optimize high-performance ML and HPC kernel software for Cerebras’ massively parallel processor architecture. Design and map new machine learning and linear algebra kernels to the WSE system, build and debug optimized low-level assembly and custom CSL routines, and use performance modeling to drive design decisions. Own validation by creating unit and system test methodologies, and collaborate with chip and system architects to tune instruction sets, microarchitecture, and IO.
Location: Anywhere
Workplace: Remote
Employment Type: Full time
Job Function: Healthcare (Clinical, Medical, Wellness)
Seniority: Mid level

Key Responsibilities

  • •Develop design specifications for new machine learning and linear algebra kernels and map them to the Cerebras WSE System using parallel programming algorithms.
  • •Build and debug a kernel library using highly optimized low-level assembly instruction and C-like (CSL) routines targeting Cerebras hardware.
  • •Develop and debug high-performance kernel routines in low-level assembly and CSL, implementing algorithms optimized for the Cerebras hardware system.
  • •Use mathematical models and performance analysis to measure software performance and inform design decisions.
  • •Develop and integrate unit and system testing methodologies to verify correct functionality and performance of kernel libraries.

Key Requirements

  • •Bachelor’s, Master’s, or PhD (or foreign equivalents) in Computer Science, Computer Engineering, Mathematics, or related fields.
  • •Comfort learning new hardware architecture details and understanding hardware architecture concepts.
  • •Proficiency in C++ and Python for implementing software components.
  • •Good knowledge of library and/or API development best practices.
  • •Strong debugging skills for complex software stacks.
Education:
Skills:DebuggingProblem-solvingAnalysis
Tech Stack:C++PythonC-like (CSL)AssemblyTensorFlowPyTorchGPUsFPGAs

Company Brief

Cerebras
Designs and builds wafer-scale AI accelerators and systems for large-scale deep learning workloads, delivering specialized hardware and software to accelerate model training and inference for enterprises and research institutions.
Industry: Hardware Devices
Company Size: Large (251 to 1,000 employees)
Growth: Scaleup
Headquarters: Sunnyvale, United States
Founded: 2016
WebsiteLinkedIn