Senior/Staff Software Engineer - Prediction Integration

Responsibilities

• You will work closely with Prediction and Planner to integrate advanced ML models and develop first-principles based safeguards, to ensure trustworthy prediction and decision making.
• You will inform and guide the development of new ML models and should be willing to dive deep and address issues in the model and data pipelines.
• You will design interfaces between prediction and planning, creating abstraction layers  that facilitate modular integration of various machine learned components within the planning architecture.
• You will create principled algorithmic improvements to specific areas of driving behavior and implement those changes in our code base.
• You will facilitate the collaborations between the prediction data/modeling teams and the planning and control teams in order to deliver architectural changes to the system.

Qualifications

• Master's or PhD degree in computer science or related field and 5+ years of relevant experience
• Fluency in modern C++ standards, programming and software design principles
• Strong knowledge of algorithmic design, implementation and optimization
• Prior experience or expertise in machine learning, either in model architecture or production data pipelines
• Demonstrated ability to communicate and collaborate cross-functionally

Bonus Qualifications

• Demonstrated ability to create real-time motion planning algorithms
• Experience with sequential decision making, including, but not limited to, imitation learning, reinforcement learning, joint trajectory prediction and planning, etc.
• Experience with machine learning and deep learning frameworks (e.g., TensorFlow, PyTorch, TensorRT) and basic knowledge of CUDA programming or willingness to learn