Inference Performance Engineer, ML Systems & Optimization

Cerebras Systems; Toronto; On-site; CAD 90,000 - 120,000; Full time

Job summary

A leading AI technology company in Toronto is seeking an experienced software engineer to join their inference model team. This role involves prototyping AI architectural tweaks, developing benchmarking automation, and collaborating closely with silicon teams. Candidates should have over 3 years of experience in high-performance software and a solid understanding of AI tools. Join the forefront of groundbreaking advancements in AI and enjoy a non-corporate culture with job stability.

Benefits

Job stability

Non-corporate work culture

Innovative AI platform development

Qualifications

• 3+ years of experience in high-performance ML or systems software.
• Familiarity with full AI toolchain: Python, compilers, performance profiling.
• Must be able to debug across performance and numerical accuracy.

Responsibilities

• Prototype and benchmark cutting-edge AI ideas.
• Develop automation for experiment design and regression triage.
• Collaborate with compiler and silicon teams on innovations.

Skills

High-performance ML or systems software

Transformer math-attention scaling

Python modeling code

Strong debugging skills

Experience with AI agents

Tools

C/C++ programming

LLVM

MLIR

Job description

A leading AI technology company in Toronto is seeking an experienced software engineer to join their inference model team. This role involves prototyping AI architectural tweaks, developing benchmarking automation, and collaborating closely with silicon teams. Candidates should have over 3 years of experience in high-performance software and a solid understanding of AI tools. Join the forefront of groundbreaking advancements in AI and enjoy a non-corporate culture with job stability.