- San Francisco, California, United States
- On-site
- Full-time
- $150K–$250K per year
- Visa sponsorship
Research and build faster kernels for AI workloads. You'll work closely with the compiler team, investigate performance bottlenecks, and take optimizations through correctness checks, benchmarking, and execution on real hardware.
Compensation
Annual base salary: $150,000–$250,000 USD. Equity: 0.15%–0.75%. Visa: Will sponsor.
Responsibilities
- Research and build faster kernels for AI workloads
- Work closely with the compiler team
- Investigate performance bottlenecks
- Take optimizations through correctness checks, benchmarking, and execution on real hardware
- Develop agent-driven systems that write, test, and improve kernels
Requirements
- Nice to have: kernel autoresearch frameworks
- Nice to have: ML compilers
- Nice to have: CUDA
- Nice to have: Triton
- Nice to have: GPU instruction sets