Senior MLSys Engineer - Kernel Optimization

OctoAI is a leading startup in the generative AI market, focused on empowering businesses to build differentiated applications with the latest AI features. As a Senior MLSys Engineer specializing in Kernel Optimization, you'll join the Automation team to develop the most efficient engine for generative model deployment.

Your role will involve:

• Developing and optimizing high-performance computing kernels for GPU acceleration
• Implementing solutions in C/C++ and Python
• Deep diving into GPU performance optimizations
• Working on kernel optimizations for CUDA or other accelerators
• Collaborating on machine learning compilers and frameworks

We're looking for candidates with:

• A degree in Computer Science, Electrical Engineering, or related field
• Strong programming skills in C/C++ and Python
• Deep understanding of GPU performance optimizations
• Experience with kernel optimizations on CUDA or other accelerators
• Contributions to innovative projects like Cutlass, FlashAttention, or vllm

OctoAI offers a comprehensive benefits package, including fully covered healthcare premiums, competitive compensation with stock options, 401(k), flexible work options, generous time off, and parental leave.

Join us in our mission to make models work for developers, allowing them to focus on building apps that wow their customers without becoming AI infrastructure experts. We value diversity, creativity, and a balanced life. If you're passionate about pushing the boundaries of AI infrastructure, we want to hear from you!