United States onlyAt Serve Robotics, we’re reimagining how things move in cities. Our personable sidewalk robot is our vision for the future. It’s designed to take deliveries away from congested streets, make deliveries available to more people, and benefit local businesses.
The Serve fleet has been delighting merchants, customers, and pedestrians along the way in Los Angeles while doing commercial deliveries. We’re looking for talented individuals who will grow robotic deliveries from surprising novelty to efficient ubiquity.
Who We Are
We are tech industry veterans in software, hardware, and design who are pooling our skills to build the future we want to live in. We are solving real-world problems leveraging robotics, machine learning and computer vision, among other disciplines, with a mindful eye towards the end-to-end user experience. Our team is agile, diverse, and driven. We believe that the best way to solve complicated dynamic problems is collaboratively and respectfully.
At Serve Robotics, we’re reimagining how things move through cities. We’re seeking a Navigation and Behavior Planning Specialist to lead the development of advanced planning technologies for semi-structured urban environments—such as sidewalks, intersections, and dense pedestrian pathways.
In this role, you’ll design and implement state-of-the-art algorithms that empower our robots to navigate complex scenarios with precision and safety. This includes real-time decision-making for dynamic interactions with pedestrians, vehicles, and other obstacles, as well as support for multi-point turns and other intricate maneuvers.
Responsibilities
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 (e.g., vision, LiDAR).
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.
Qualifications
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.
What makes you standout
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.
