Engineering Manager - Behavior

Applied Intuition Applied Intuition · Robotics · Sunnyvale, CA · SDS Software Engineering

Engineering Manager for SDS Behavior team, leading a team to build and deploy scalable behavior systems for autonomous vehicles (cars, trucks, etc.). Owns architecture and delivery of next-generation behavior planning systems for L2 and L4 autonomous vehicles, focusing on complex environments and diverse ODDs. Involves driving architectural and business decisions, customer partnerships, team mentoring, and owning a significant portion of the autonomy stack.

What you'd actually do

  1. Drive the overall strategy, technical roadmap, and architecture for behavior planning dedicated to L2 and L4 autonomous vehicles for cars, trucks, mining & construction, and offroad
  2. Guide the design and implementation of robust, safety-critical algorithms for various driving domains, including urban streets, highways, dirt roads, and diverse environmental conditions
  3. Grow and manage a team of world class engineers in the field of behavior systems
  4. Evolve the architecture to achieve the final goal of an L4 end-to-end stack
  5. Work cross functionally with other teams, including Perception, Research, Simulation, and Vehicle Operations, to ensure the robust and efficient integration of the behavior software stack

Skills

Required

  • 5+ years of experience in robotics or autonomous systems, with a focus on behavior systems
  • Experience in two or more of the following: behavior planning, decision making under uncertainty, path planning, motion planning, probabilistic reasoning, prediction, machine learning, trajectory generation, mapless driving, end-to-end autonomy stack
  • Demonstrated ability to architect large-scale, production software for real-world robotic or automotive systems
  • Proven leadership experience managing engineering teams, setting goals, and overseeing technical projects
  • Strong communication and problem-solving skills

Nice to have

  • Direct experience working in end-to-end autonomy
  • Hands-on experience building ML-driven and rule-based behavior planning (and their interplay), intent detection, or risk assessment modules
  • Demonstrated success in applying machine learning and AI processes to complex decision-making frameworks for autonomous vehicles

What the JD emphasized

  • behavior planning
  • decision making under uncertainty
  • path planning
  • motion planning
  • probabilistic reasoning
  • prediction
  • machine learning
  • trajectory generation
  • end-to-end autonomy stack
  • safety-critical algorithms
  • L4 end-to-end stack

Other signals

  • behavior planning
  • decision making under uncertainty
  • path planning
  • motion planning
  • probabilistic reasoning
  • prediction
  • machine learning
  • trajectory generation
  • end-to-end autonomy stack