All positions

ML Compiler

Machine Learning San Francisco Full-Time On-Site

Optimize and deploy ML models for real-time inference on robotic hardware.

What you'll do

  • Build compilation and optimization pipelines for ML models
  • Optimize inference latency and throughput for edge deployment
  • Develop custom kernels and operators for target hardware
  • Profile and debug model performance across platforms
  • Collaborate with ML researchers to enable efficient architectures

What we're looking for

  • Experience with ML compilers (TVM, XLA, TensorRT, or similar)
  • Strong systems programming skills in C++ and Python
  • Knowledge of GPU/accelerator architectures
  • Experience optimizing neural network inference
  • BS or MS in Computer Science or related field
Apply for this role