The Motion Planning Research team is specialized in fusion of Machine Learning and Classical Methods, researches new deep learning approaches, builds deep neural networks, algorithms, and software to impact across navigation, behavior, route planning, as well as trajectory optimization, numerical optimization, and model predictive control. The team creates proof of concepts and once an idea is effective, works to put then into production.
Motional's Machine Learning team has produced ground breaking advancements in the autonomous vehicle industry including nuPlan (https://arxiv.org/abs/2106.11810), nuScenes (https://www.nuscenes.org), PointPillars (https://arxiv.org/abs/1812.05784), and PointPainting (http://arxiv.org/abs/1911.10150)
What You'll Do:
- Contribute to cutting edge motion planning system and deep learning system
- Create python-based automated pipeline to train, evaluate and deploy machine learning models to the vehicle
- Develop large scale training pipeline for machine learning models
- Contribute to automatic data mining to find interesting and impactful data
- Research metrics and model introspection
- Train and evaluate models in distributed fashion
- Deploy models on vehicle and evaluate their performance with metrics
What You'll Bring:
- Masters or PhD in Machine Learning, Computer Science, Applied Mathematics, Statistics, Physics or a related field with 3+ years of relevant experience
- 5+ years of software development experience.
- Python and Python bindings development experience
- Advanced knowledge of software engineering principles including software design, source control management, build processes, code reviews, testing methods.
- Experience with PyTorch or other deep learning frameworks
- You believe that you can achieve more on a team -- that the whole is greater than the sum of its parts
- Passion about self-driving technology and its potential impact on the world
- Leadership and mentoring experience