- Palo Alto, California, United States
- Full-time
- $200K–$400K per year
- 4+ years
Member of Technical Staff – Inference-Multi-Hardware to push the limits of performance for frontier AI systems.
Compensation
Depending on background, skills, and experience, the expected annual salary range for this position is $200,000 - $400,000 USD + equity.
Responsibilities
- Bring up RadixArk's inference and training systems on new accelerator platforms and drive them to competitive performance
- Design hardware abstractions that let a single codebase stay fast across vendors without forking
- Port and optimize kernels across programming models and memory architectures
- Build cross-platform benchmarking, profiling, and regression detection so performance claims hold up on every target
- Debug numerical divergence and correctness gaps between platforms
Requirements
- Nice to have: more than one vendor ecosystem
- Nice to have: compiler stacks (XLA, MLIR, TVM, Triton)
- Nice to have: hardware abstraction layers
- Nice to have: quantization
- Nice to have: mixed-precision
