LLM Inference Performance & Evaluation Engineer

Cerebras; Toronto; On-site; CAD 90,000 - 130,000; Full time

Job summary

A leading AI technology company in Toronto is seeking a skilled individual to join their inference model team, focusing on prototype architectural tweaks and performance evaluation. Ideal candidates will have a strong background in high-performance ML or systems software, a deep understanding of Transformer technology, and skills in automation. The role offers an exciting opportunity to advance AI technology and work on a groundbreaking platform that reshapes the industry.

Qualifications

• 3+ years of experience in building high-performance ML or systems software.
• Solid grounding in Transformer math, or ability to learn quickly.
• Prior experience in modeling, compilers, or benchmarks.

Responsibilities

• Prototype and benchmark cutting-edge ideas in ML.
• Develop automation for experiment design and run scheduling.
• Work closely with various technical teams for software/hardware integration.

Skills

High-performance ML or systems software

Transformer math

Python modeling code

Strong debugging skills

Automation and workflow orchestration tools

Tools

C/C++ programming

LLVM and/or MLIR

Job description

A leading AI technology company in Toronto is seeking a skilled individual to join their inference model team, focusing on prototype architectural tweaks and performance evaluation. Ideal candidates will have a strong background in high-performance ML or systems software, a deep understanding of Transformer technology, and skills in automation. The role offers an exciting opportunity to advance AI technology and work on a groundbreaking platform that reshapes the industry.