Machine Learning Engineer (Model Bring-Up)
Core
Take ML models from reference implementation to efficient execution on AI accelerator hardware, optimizing performance across compilers, kernels, and runtime.
Role type
Senior IC machine learning engineer (compiler & systems)
Builds
Efficient model execution paths on Cerebras AI accelerators
Domain
AI hardware, compiler engineering, high-performance inference
Deliverable
production ML models
Required skills
C++, Python, PyTorch, MLIR, compiler fundamentals, transformer architectures, profiling, numerical validation
Preferred skills
LLM inference (GQA, MoE, KV cache), low-bit quantization, accelerator kernel development, distributed execution, open-source contributions
Technologies
MLIR, LLVM, PyTorch, Cerebras WSE
Responsibilities
Implement supported execution paths and establish correctness against reference implementations; Develop and extend MLIR dialects and lowering passes; Enable operators through compiler and kernel changes; Improve operator fusion, tensor layouts, and parallel execution; Tune prefill/decode performance and quantization; Investigate numerical differences and measure accuracy impact; Identify compute, memory, and runtime bottlenecks using profiling tools
Seniority
Senior, hands-on IC
