Staff Software Engineer - Machine Learning

General Motors

13d•$134,000 - $235,900•Hybrid

About The Position

The Smart Agents group is responsible for building the ML models and system to simulate road users in a variety of situations and generate the scenarios used for testing and training AV driving policies. If you think of Simulation as a video game our autonomous vehicles train on to learn to drive, the Smart Agents team develops the ML/AI models that control the other characters in the video game to interact in realistic ways as the av drives-eg, the other vehicles, bikers, and pedestrians. Our technology stack includes Generative AI models (GPT) and Reinforcement Learning (RL) policies. The Smart Agents group work closely with the rest of the Simulation, and our partners Behaviors, Perception, and Safety Engineers. The specific duties may include ML/RL model development as well as training loop development, streamlining optimization, integration, creating ML infrastructure, metrics, and data pipelines for production model deployment as well as for fast experimentation cycles.

Requirements

4+ years of experience in the field of robotics or latency-sensitive backend services
Background working with machine learning teams, algorithms, and models
Proven experience in machine learning and classification.
Familiar with ML frameworks such as Tensorflow or PyTorch
Experience building highly performant ML and system pipelines
Strong programming skills in modern C++ or Python
Experience with profiling CPU and/or GPU software, process scheduling, and prioritization
Passionate about self-driving car technology and its impact on the world
Expertise in setting architectures that are scalable, efficient, fault-tolerant, and are easily extensible allowing for changes overtime without major disruptions.
Ability to design across multiple systems.
Ability to both investigate in sophisticated areas as well as a good breadth of understanding of systems outside of your domain.
Ability to wear several hats shifting between coding, design, technical strategy, and mentorship combined with excellent judgment on when to switch contexts to meet the greatest need.
Track record in deploying perception/prediction/av models into real world environments
Experience working with RL and sequence prediction (ML) models

Nice To Haves

Experience in simulation and robotics is highly desirable, with a preference for candidates from AV or robotics backgrounds rather than solely cloud-focused companies.
Bonus: Experience building highly performant ML and system pipelines
Bonus: Experience with profiling CPU and/or GPU software, process scheduling, and prioritization

Responsibilities

Support the team in developing machine learning (ML) and reinforcement learning (RL) models, including training loop development and optimization.
Streamline integration and create ML infrastructure, metrics, and data pipelines for production model deployment and rapid experimentation.
Work as part of an ML team and contribute strong software engineering (SWE) expertise.
Support the ML team in accelerating project timelines, particularly in areas related to Autopilot, Lane Keep, and autonomous vehicle (AV) technologies.