We are looking to add a highly talented Prediction and Behavior Modeling Research Scientist to help us build probabilistic models of the future state of the world (e.g., cars, pedestrians, and other road users). As a Sr. Research Scientist, you will use real-time perception data and prior knowledge to estimate how the world around us will change, so that the planner can make better decisions. Your applied mathematics, data analytics, and machine learning experience will inform your pragmatic approach to making a more intelligent autonomous vehicle. Does this sound like you?
The Motional Pittsburgh office is located in the new Hazelwood Green development at 4734 Second Avenue, a culmination of the city’s goal of restoring an economic driver to the neighborhood in a thoughtful, inclusive, and sustainable way. With views along the Monongahela river, the Pittsburgh office is in the heart of this new state of the art development.
What you’ll be doing:
- Dive into data to understand behaviors of road users such as cars, bikes, and pedestrians; leverage machine learning methods where appropriate
- Develop probabilistic models to predict how other road users may move and interact with our car, and evaluate their performance on real-world and simulated data sets
- Translate generated algorithms into production-level code
- Collaborate with Planning and Perception teams to achieve objectives in improving system performance
What we're looking for:
- MS or PhD in computer science, robotics, or similar field, with 3+ years practical experience in robotics, machine learning, and analysis of large data sets.
- Fluency in Python, including standard scientific computing libraries
- Experience working with large data sets
- Experience using modern software engineering tools (e.g., version control, CI)
- Strong applied math background
Bonus points (not required):
- In-depth understanding of common Machine Learning and Deep - Learning algorithms (e.g., for classification, regression, and clustering)
- Experience developing autonomous vehicles or robots
- Experience in a regulated, safety critical environment
- Strong C++ development skills
- Publications and patents encouraged. Team has one paper currently at CVPR (https://arxiv.org/abs/1911.10298).
- Joining a small team of 10, which offers the opportunity to contribute across multiple disciplines (perception, prediction, planning, infrastructure).
- Speaking opportunities are encouraged and supported
- Will closely collaborate with ML team for infrastructure and prototype