Software Engineer - GPU Kernels

Highlights

• Your code directly impacts performance of state-of-the-art ML models.
• Work on the fastest embeddings inference solution available.
• Contribute to internal and open-source GPU libraries.

What they offer

• 100% coverage of medical, dental, and vision insurance for employee and dependents
• Flexible PTO policy including company wide Winter Break
• Paid parental leave
• Fertility and family-building stipend through Carrot (U.S. only)
• Company-facilitated 401(k)
• Exposure to a variety of ML startups for learning and networking

Ideal candidate

Low-level performance enthusiast who thrives on microsecond optimizations and high-impact systems work. Motivated collaborator excited to push AI acceleration forward and share ideas with the community.

Requirements

• Strong understanding of GPU architecture and programming paradigms
• Knowledge of GPU memory hierarchy, thread/block/grid organization and synchronization
• Proficient in C++ and GPU performance profiling tools
• Knowledge of CUDA C++ API and memory access and bandwidth optimization
• Knowledge of numerical precision and quantization strategies
• Familiarity with modern GPU features like tensor cores and async operations