- Milpitas, California, United States
- On-site
- Full-time · Senior
- $185K–$325K per year
- 4+ years
- Visa sponsorship
Lead end‑to‑end optimization of embodied AI inference pipelines for edge robotics.
Compensation
Compensation: Salary $185,000–$325,000 USD + Bonus + Equity
Responsibilities
- Develop and optimize inference pipelines for embodied AI models targeting real‑time execution on edge hardware
- Implement CUDA‑level optimizations including custom kernels, memory layout tuning, and hardware‑aware graph compilation
- Apply and advance model compression techniques to achieve production‑grade throughput on constrained devices
- Profile and debug end‑to‑end inference stacks using tools such as NSight, TensorRT, and Triton
- Collaborate with ML research and robotics teams to co‑design model architectures that meet real‑time control‑loop latency requirements
Requirements
- Master's degree in Computer Science, Electrical Engineering, or related field
- PhD degree
- Nice to have: embodied AI models (VLA, multimodal transformers, diffusion‑based policies)
- Nice to have: compiler‑based optimization pipelines such as XLA, torch.compile, MLIR
- Nice to have: understanding of robotics system constraints