Senior ML Performance Engineer — Build & Benchmark Optimized AI

Lemurian Labs; Toronto; On-site; CAD 60,000 - 80,000; Full time

Job summary

A technology company focused on AI in Toronto seeks a Senior ML Performance Engineer to architect a performance testing platform. You will measure and optimize the performance of large language models on GPUs. The role requires extensive experience in performance engineering and knowledge of ML frameworks. Ideal candidates will have strong programming skills in Python and C/C++. Additional benefits include equity options, medical, and retirement savings plans.

Benefits

Equity

Company bonus opportunities

Medical benefits

Dental and vision benefits

Retirement savings plan

Supplemental wellness benefits

Qualifications

• 7+ years of experience in performance engineering or systems engineering roles.
• Deep understanding of ML inference workloads, particularly transformer-based models.
• Hands-on experience with GPU programming and optimization.

Responsibilities

• Design performance testing platform for evaluating LLM inference workloads.
• Define benchmarking methodology, metrics, and test suites.
• Establish baseline performance for unoptimized models.

Skills

Performance engineering

GPU programming

Python

C/C++

Machine Learning frameworks

Benchmarking

Tools

CUDA

ROCm

CI/CD systems

Docker

Job description

A technology company focused on AI in Toronto seeks a Senior ML Performance Engineer to architect a performance testing platform. You will measure and optimize the performance of large language models on GPUs. The role requires extensive experience in performance engineering and knowledge of ML frameworks. Ideal candidates will have strong programming skills in Python and C/C++. Additional benefits include equity options, medical, and retirement savings plans.