Senior Machine Learning Engineer, Motion Planning

RESPONSIBILITIES:

• Motion Planning ML model R&D by prototyping, validating and iterating on existing and new model architectures leveraging imitation learning, deep reinforcement learning, and large-scale data.
• Own development of new ML models end-to-end from data strategy, initial development, optimization, production platform validation, and fine tuning based on metrics and on road performance.
• Lead large, multi-person projects and significantly influence the overall Motion Planning architecture and technical direction.
• Enable and help other engineers on the team to be more effective through coaching and leading by example when it comes to writing high-quality code, providing high-quality code and design document reviews and delivering rigorous reports from ML experiments.
• Work in a high-velocity environment and employ agile development practices.
• Team player and "get things done" mentality
• Collaborate closely with teams such as Perception, Simulation, Infrastructure, Tooling to drive unified solutions.
• Closely collaborate with Motion Planning subteams to develop end-to-end solutions.

EXPERIENCE:

• MS, or higher degree, in Machine Learning, Robotics, CS (or other related fields), or other quantitative fields or equivalent in industry experience.
• 5+ years of experience with ML frameworks such as PyTorch, Caffe, Tensorflow
• Extensive experience with learning-based planning approaches like imitation learning, reinforcement learning and state-of-the-art techniques for sequential modeling like Transformer architectures, and camera input or vector/point-based representations.
• Strong programming skills in Python or C++
• 5+ years of experience in machine learning workflows: data sampling and curation, pre-processing, model training, ablation studies, evaluation, deployment, inference optimization.
• Passionate about self driving car technology and its potential for humanity.
• Strong communication skills and ability to communicate concepts clearly and precisely

Nice to Have

• Experience with robot motion planning techniques like trajectory optimization, sampling-based planning, model predictive control, etc or self-driving problems (Perception, Prediction, Mapping, Localization, Planning, Simulation)
• Experience in writing production level code in a real-time operating system.
• Experience with temporal/sequential modeling and/or reinforcement learning.
• Experience in optimizing runtime-critical systems for Linux, UNIX-like real-time operating systems on automotive-grade compute platforms, and building safety-critical software architecture.