Research Scientist, Learnable Planner

Waabi Waabi · Robotics · US & Canada, Dallas, TX +4 · Remote · Autonomy & Algorithms

Research Scientist focused on developing deep learning-based motion planning for autonomous trucks, leveraging and advancing state-of-the-art robotics and ML techniques, including imitation and reinforcement learning, planning, perception, prediction, simulation, and foundation models. The role involves contributing to a scalable planning solution and a high-fidelity simulator, with a requirement to publish research externally and support deployment to production systems.

What you'd actually do

  1. Design and execute on a research agenda for deep-learning based motion planning for self-driving.
  2. Leverage and advance the state-of-the-art in robotics and machine learning to enable safe self-driving at scale, with advanced techniques in imitation and reinforcement learning, planning and search, perception and prediction, simulation, foundation models and more.
  3. Support deploying solutions to our production systems, collaborating closely with platform teams to ensure seamless integration of research findings into production systems.
  4. Stay up-to-date and advance beyond the state-of-the-art in artificial intelligence, machine learning, computer vision, and self-driving technologies.
  5. Champion engineering excellence, ensuring high-quality, well structured and tested code.

Skills

Required

  • MS/PhD degree in Computer Science, AI, Machine Learning, Computer Vision, Robotics and/or similar technical field(s) of study
  • Experience in planning/decision making approaches (e.g., imitation learning, reinforcement learning, optimal control, optimization based approaches, search methods, probabilistic decision making)
  • Demonstrated research experience through previous internships, work experience, research projects, and papers at top conferences
  • Strong quantitative background and coursework in or working knowledge of linear algebra, calculus, and probability
  • Proficient in reading and coding in Python

Nice to have

  • Previous experience in self-driving technology
  • Experience deploying ML/DL models to a production motion planning or related robotics stack
  • Proficiency in Pytorch, Rust, C++ and/or CUDA

What the JD emphasized

  • research agenda
  • state-of-the-art
  • production systems
  • publish work externally

Other signals

  • research agenda for deep-learning based motion planning
  • advance the state-of-the-art in robotics and machine learning
  • deploying solutions to our production systems
  • advance beyond the state-of-the-art in artificial intelligence, machine learning, computer vision, and self-driving technologies
  • publish work externally at top machine learning, computer vision, and robotics conferences