Senior Manager, ML Occupancy Modeling, Autonomy

Rivian Rivian · Auto · Palo Alto, CA · Autonomous Driving

Senior Manager to build and lead a team focused on occupancy modeling as a core output of an end-to-end autonomy model. The team will develop learned representations of the driving scene to support safe and scalable autonomous driving. Responsibilities include defining the roadmap, guiding model development, training, evaluation, debugging, and deployment of large-scale autonomy ML systems.

What you'd actually do

  1. Build and lead a small, high-performing ML team focused on occupancy outputs for our end-to-end autonomy model.
  2. Define the roadmap for occupancy modeling, including freespace, static and dynamic occupancy, occlusion reasoning, uncertainty, and future scene evolution.
  3. Partner closely with perception, planning, simulation, data, and ML infrastructure teams to make occupancy outputs useful for real-world autonomy.
  4. Guide model development, training, evaluation, debugging, and deployment of large-scale autonomy ML systems.
  5. Establish clear metrics and workflows that connect occupancy quality to downstream planning, safety, and closed-loop performance.

Skills

Required

  • B.S., M.S., or Ph.D. in Computer Science, Robotics, Machine Learning, or a related field.
  • 8+ years of experience building ML systems, ideally in autonomy, robotics, perception, prediction, planning, or simulation.
  • Experience managing or technically leading ML engineers or researchers.
  • Strong understanding of modern autonomy ML systems, including transformer models, multi-task learning, sensor fusion, or end-to-end driving models.
  • Experience with learned scene representations such as occupancy, freespace, BEV perception, semantic maps, trajectories, or world models.
  • Strong ability to turn ambiguous technical problems into clear team roadmaps and execution plans.
  • Strong engineering background, with fluency in Python and experience working with production ML systems.

What the JD emphasized

  • occupancy modeling
  • end-to-end autonomy model
  • learned scene representations
  • transformer models
  • multi-task learning
  • sensor fusion
  • end-to-end driving models
  • occupancy, freespace, BEV perception, semantic maps, trajectories, or world models

Other signals

  • end-to-end autonomy model
  • occupancy modeling
  • learned scene representations
  • transformer models