Senior Inference Performance Engineer - GPU & CUDA

inference.net; San Francisco (CA); Hybrid; USD 220,000 - 320,000; Full time

Benefits offered by this job

Equity in a high-growth startup

Comprehensive benefits

Job summary

inference.net, a growing company in San Francisco, seeks an experienced engineer to optimize AI inference performance. The ideal candidate will have over 2 years of experience in ML systems and GPU programming. Key responsibilities include implementing optimization techniques and debugging inference frameworks. The role offers a competitive salary of $220,000 - $320,000 plus equity, and values curiosity and fast learning. You will join a team devoted to innovative AI solutions.

Qualifications

• 2+ years of experience in ML systems, inference optimization, or GPU programming.
• Strong proficiency in Python and familiarity with C++.
• Hands-on experience with LLM inference frameworks.

Responsibilities

• Implement and productionize optimization techniques.
• Deep dive into inference frameworks to debug and improve performance.
• Profile and optimize CUDA kernels and GPU utilization.

Skills

Machine Learning systems

Inference optimization

GPU programming

Python

C++

LLM inference frameworks

GPU architecture

Performance improvement

Tools

PyTorch

CUDA

Docker

Kubernetes

Job description

inference.net, a growing company in San Francisco, seeks an experienced engineer to optimize AI inference performance. The ideal candidate will have over 2 years of experience in ML systems and GPU programming. Key responsibilities include implementing optimization techniques and debugging inference frameworks. The role offers a competitive salary of $220,000 - $320,000 plus equity, and values curiosity and fast learning. You will join a team devoted to innovative AI solutions.