Software Engineer, AI Solutions

Job Description

Remote: This role is based remotely but if you live within a 50-mile radius of Atlanta, Austin, Detroit, Warren, Milford or Mountain View, you are expected to report to that location three times a week, at minimum. 

Role: The AI Solutions team in the GM AV Organization is responsible for end-to-end deployment of machine learning models for inference from frameworks (e.g. PyTorch) to the autonomous vehicle hardware platform, as well as the ML runtime software needed to execute those models on the vehicle. We work closely with partners in the Embodied AI org, as well as AI Kernels, AI Compilers, and AI Architecture. This role blends expertise in ML systems, model serving, software optimization, operating systems, and hardware-aware engineering.  

What You’ll Do:

• Deploy machine learning (ML) models that drive self-driving vehicles by leveraging ML compilers, hardware-aware ML optimizations, and ML runtimes, targeting both onboard (vehicle) and offboard (cloud/simulation) environments.  

• Develop low-level ML runtime software and APIs to efficiently serve and execute models in onboard and offboard environments.  

• Collaborate with engineers from Embodied AI, Kernels, Compilers, Architecture, and System Performance teams.  

Additional Job Description

Your Skills & Abilities:

• Strong system fundamentals and coding abilities (C++, Python)  

• Experience in ML model optimization, deployment, runtimes, or serving infrastructure  

• Background in computer architecture and operating systems  

• Experience with optimizing and/or evaluating complex software systems on dedicated hardware  

• Understanding of how to design high-performant software components  

• Excellent interpersonal skills  

• 2+ years of relevant industry experience  

• Experience developing in a Linux environment  

• BS, MS or PhD in CS, or related technical field  

What Will Give You A Competitive Edge:  

• Experience with NVIDIA GPUs and CUDA  

• Experience with low latency or real time systems  

• Familiarity with ML hardware and performance of inference on ML hardware  

• Experience with lower-levels of an accelerator software stack (i.e. drivers, runtimes, and user-level API) and the inter-layer interactions  

• Experience in the AV industry 

Compensation: The compensation information is a good faith estimate only. It is based on what a successful applicant might be paid in accordance with applicable state laws. The compensation may not be representative for positions located outside of New York, Colorado, California, or Washington.   

• The salary range for this role is $116,000 to $178,000. The actual base salary a successful candidate will be offered within this range will vary based on factors relevant to the position.  

• Bonus Potential: An incentive pay program offers payouts based on company performance, job level, and individual performance.