Senior ML Infrastructure Engineer - Autonomy & Optimization

Nuro; California (MO); On-site; USD 194,000 - 352,000; Full time

Job summary

Nuro is seeking an Autonomy ML Infrastructure Engineer to advance the core ML optimization stack for our self-driving platform. You will design, implement, and deploy model pipelines, quantization, distillation, and compiler-driven optimizations, collaborating with cross-functional teams across perception, behavior and mapping.

Ideal candidates have 3+ years in ML optimization, strong Python and C++/CUDA skills, and experience with PyTorch or TensorFlow.

Qualifications

• 3+ years of relevant experience in ML optimization infrastructure.
• Experience with ML optimization techniques such as quantization and pruning, and ML compilers.
• Experience maintaining, profiling, and optimizing GPU ML compilers & runtimes.
• Proficient in Python and working experience with C++ and CUDA.
• Working experience deep learning frameworks (like PyTorch, Jax, Tensorflow, Keras).
• Proficient in Python and working experience with C++.
• You are passionate about accelerating the benefits of robotics for everyday life.

Responsibilities

• Optimize Nuro’s autonomy stack with cutting-edge optimization techniques like quantization, distillation, and model compression.
• Work with autonomy engineers to optimize, validate, and deploy large language models.
• Develop and maintain a world-class model compiler framework, FTL.
• Write robust, high quality software to increase our confidence in our vehicle’s ability to navigate safely on-road.
• Collaborate closely with machine learning domain experts and engineers across behavior, perception and mapping to design and implement end-to-end learned ML solutions.

Skills

ML optimization

Python

C++

CUDA

PyTorch

Jax

TensorFlow

Keras

Model compression

Quantization

Pruning

FTL

Tools

FTL

GPU profiling tools

Job description

Nuro is seeking an Autonomy ML Infrastructure Engineer to advance the core ML optimization stack for our self-driving platform. You will design, implement, and deploy model pipelines, quantization, distillation, and compiler-driven optimizations, collaborating with cross-functional teams across perception, behavior and mapping.

Ideal candidates have 3+ years in ML optimization, strong Python and C++/CUDA skills, and experience with PyTorch or TensorFlow.