ML Inference Performance Engineer - Kernel Optimizer

Cerebras Systems; United States; On-site; USD 110,000 - 150,000; Full time

Job summary

Cerebras Systems is seeking engineers for the inference performance team, focusing on optimizing AI model inference speed on the world’s largest AI chip. This role involves performance modeling, debugging, and tooling development to enhance machine learning capabilities.

Ideal candidates should have a relevant degree, strong experience in computer architecture, and proficiency in C++ and Python. Join us at Cerebras to help shape the future of AI technology.

Qualifications

• Strong background in computer architecture.
• Exposure to and understanding of low-level deep learning / LLM math.
• 3+ years of experience in a relevant domain.

Responsibilities

• Build performance models to estimate ML model performance.
• Optimize and debug kernel micro code for higher inference speed.
• Develop tools to visualize performance data.

Skills

Kernel optimization

C++

Python

Performance profiling

Problem-solving

Education

Bachelors / Masters / PhD in Electrical Engineering or Computer Science

Tools

CPU/GPU simulators

Job description

Cerebras Systems is seeking engineers for the inference performance team, focusing on optimizing AI model inference speed on the world’s largest AI chip. This role involves performance modeling, debugging, and tooling development to enhance machine learning capabilities.

Ideal candidates should have a relevant degree, strong experience in computer architecture, and proficiency in C++ and Python. Join us at Cerebras to help shape the future of AI technology.