About The Role
In this role, you will be working as a member of the Behavior team and leveraging the cutting edge of machine learning research to solve challenging real-world robotics problems. This role will be focused on bringing advancements in the field of foundational model and Multimodal Large Language Modeling to the AV domain. This role requires working with and developing large generative models, in conjunction with a variety of input modalities, keeping up to date and experimenting with state-of-the-art models quickly and efficiently, collaborating with other teams to determine data and infrastructure support needs, and working with others to improve model optimization and inference speeds. You will use your applied research skills to think through the creation and deployment of these foundational models and LLMs on autonomous vehicles while working talented researchers in the field. If you love solving challenging new problems and deploying solutions on robots used in the real world (like a car that can talk to you!), come join us!
About The Work
- Work on generative foundational and large language models for AV reasoning and planning
- Experiment quickly and fail fast while leveraging state-of-the-art models and techniques
- Research solutions to some of the most challenging problems in AVs and LLMs
- Collaborate with autonomy teams to understand top autonomy challenges and design roadmaps to solving these challenges using holistic solutions.
- Work with autonomy and infrastructure teams to build effective and efficient data, training, evaluation, and labeling pipelines
- Develop practical solutions and deploy them to the NuroDriver on-road!
About You
You have deep expertise and prior experience in some or many of the following areas:
- You have an M.Sc. or Ph.D. (preferable) in addition to 3+ years of experience focusing on one or more of the following areas: Computer Science, Artificial Intelligence, Mathematics, or a closely related field
- You have subject matter expertise and research in one or more of the following areas: Machine Learning (required), Large Language Modeling (required), Multimodal LLMs (e.g. visual, audio, lidar, radar), Human Preference Feedback/Reward Modeling, Knowledge Distillation, Robotics
- You have strong problem solving and programming skills in Python (required) and C++ (preferable) and utilize coding best practices as a part of your work
- Independent researcher able to push multi-faceted projects forwards, collaborate across organizations, and deliver results in a timely manner
- Demonstrated research publications at major conferences (RSS, ICRA, CoRL, CVPR, ICLR, ICML, NeurIPS, ICCV, AAAI, etc.)
- Strong culture fit and good team player