High-Performance ML Runtime & Kernel Engineer

Cerebras Systems; Sunnyvale (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Cerebras Systems is seeking an engineer for the Core ML team to bridge cutting-edge research with efficient execution on the Cerebras Wafer-Scale Engine.

You will work across ML frameworks, compilers, runtimes, and low-level kernels to turn research prototypes into robust, high-performance demonstrations. Depending on background, emphasis may be on runtime capabilities, kernel development, or both, contributing to scalable, real-time AI workloads.

Qualifications

• Bachelor’s, Master’s, or PhD in CS/CE/EE or related field.
• Experience developing high-performance systems software.
• Strong C++ and Python programming skills.
• Familiarity with PyTorch or JAX.
• Ability to translate research into production software.

Responsibilities

• Design and implement runtime components and high-performance kernels for Core ML.
• Translate research prototypes into Cerebras platform implementations.
• Profile and debug performance across ML stack layers.
• Optimize compute, memory, and communication for large-scale training.
• Develop benchmarks, instrumentation, and tests for correctness.

Skills

C++

Python

Performance profiling

Parallel programming

Debugging

PyTorch

JAX

Production deployment

Education

Bachelor's/Master's/PhD in CS/CE/EE

Tools

CUDA

Triton

LLVM

Job description

Cerebras Systems is seeking an engineer for the Core ML team to bridge cutting-edge research with efficient execution on the Cerebras Wafer-Scale Engine.

You will work across ML frameworks, compilers, runtimes, and low-level kernels to turn research prototypes into robust, high-performance demonstrations. Depending on background, emphasis may be on runtime capabilities, kernel development, or both, contributing to scalable, real-time AI workloads.