Serve Robotics is looking for a Lead Software Engineer, Navigation and Behavior Planning to lead the development of advanced planning technologies for semi-structured urban environments. You will design and implement state-of-the-art algorithms for autonomous sidewalk robots to navigate complex scenarios with precision and safety.

What You'll Do

Design and implement advanced planning and control algorithms for autonomous sidewalk robots operating in complex urban environments.
Collaborate cross-functionally with mapping, perception, and sensor fusion teams to build robust dynamic agent prediction models, and tightly integrate them into the planning pipeline.
Develop a semantic navigation stack that couples planning algorithms with rich semantic understanding from multi-modal sensor inputs.
Drive improvements to the robot’s ability to handle failure scenarios, correct inefficiencies, and compose low-level robotic skills into high-level, goal-directed behaviors.
Lead testing and validation efforts in both simulation and real-world deployments, ensuring planning systems are reliable, safe, and performant.
Maintain clear and comprehensive documentation of algorithms, codebases, interfaces, and system designs to support cross-team collaboration and long-term maintainability.

What We're Looking For

Master’s degree and 5+ years of experience in Robotics, AI, Computer Science, Mathematics, or a related field.
Strong foundation in behavior planning methods, including state machines, behavior trees, policy learning, and probabilistic planning.
Proven experience debugging and resolving long-tail edge cases in real-world autonomous systems through targeted behavior planning strategies.
Working knowledge of machine learning techniques, particularly as applied to dynamic agent prediction and planning.
Proficient in writing efficient, scalable, and robust code in C++ and Python.
Excellent written and verbal communication skills, with the ability to articulate technical concepts clearly across teams.

Nice to Have

PhD and 7+ years of experience in Robotics, AI, Computer Science, Mathematics, or a related field.
Hands-on experience with motion planning and control algorithms for autonomous mobile robots.
Familiarity with reinforcement learning techniques for planning and control, including imitation learning and policy optimization.
Background in integrating learning based motion planners with traditional planning pipelines for adaptive, real-time behavior.
Proven ability to design and scale simulation environments using tools like Gazebo and NVIDIA Isaac Sim for development and validation of planning systems.
Experience with modern software development workflows, including the Bazel build system and CI/CD pipelines for deploying production-grade autonomy stacks.