Co-Design & Next-Gen AI Performance Engineer

Foundation Capital; Toronto; On-site; CAD 110,000 - 170,000; Full time

Job summary

Cerebras Systems builds an AI hardware platform designed to accelerate model training and inference at scale. The role focuses on characterizing, analyzing, and optimizing performance of state-of-the-art AI models running on Cerebras’ WSE hardware.

You will work across hardware and software to identify bottlenecks, improve efficiency, and influence next-generation architecture and software systems. Strong background in architecture and DL math is valued.

Qualifications

• Bachelors / Masters / PhD in Electrical Engineering or Computer Science.
• Exposure to and understanding of low-level deep learning / LLM math.
• Strong analytical and problem-solving mindset.
• 3+ years of experience in a relevant domain (Computer Architecture, CPU/GPU Performance, Kernel Optimization, HPC).
• Experience working on CPU/GPU simulators.
• Exposure to performance profiling and debug on any system pipeline.
• Comfort with C++ and Python.

Responsibilities

• Bring up and optimize performance on new generations of the Cerebras WSE.
• Build performance models (kernel-level, end-to-end) to estimate the performance of state of the art and customer ML models.
• Optimize and debug our kernel micro code and compiler algorithms to elevate ML model inference speed, throughput and compute utilization on the Cerebras WSE.
• Debug and understand runtime performance on the system and cluster.
• Develop tools and infrastructure to help visualize performance data collected from the Wafer Scale Engine and our compute cluster.

Skills

C++

Python

Performance profiling

Kernel optimization

Computer architecture

HPC

CPU/GPU performance

Deep learning / LLM math

Education

Electrical Engineering or Computer Science degree

Tools

CPU/GPU simulators

Job description

Cerebras Systems builds an AI hardware platform designed to accelerate model training and inference at scale. The role focuses on characterizing, analyzing, and optimizing performance of state-of-the-art AI models running on Cerebras’ WSE hardware.

You will work across hardware and software to identify bottlenecks, improve efficiency, and influence next-generation architecture and software systems. Strong background in architecture and DL math is valued.