Software Engineer, ML Infrastructure, Optimization

Optimize the autonomy ML stack by applying quantization, pruning, and low-precision inference techniques to reduce latency and memory usage.
Collaborate with autonomy engineers across perception, behavior, and mapping to validate, integrate, and deploy end-to-end ML solutions.
Develop and maintain a world-class model compiler framework, FTL, to accelerate model lifecycles from training to on-robot deployment.
Write robust, high-quality software that increases confidence in on-road navigation and safety.
Contribute to deploying large language models and other ML models tailored for autonomous systems.
Bring strong Python and C++ programming skills and hands-on experience with PyTorch, Jax, TensorFlow, or Keras.