Cssmerge Robotics Planning Engineer at Pronto AI developing high-level autonomy systems for fleet coordination of autonomous haul trucks. Responsible for motion planning, multi-vehicle coordination, and fleet planning algorithms.
Responsibilities
We're looking for a Robotics Planning Engineer to develop the high-level autonomy systems that coordinate fleets of autonomous haul trucks in mining environments. You'll work on path planning, multi-vehicle coordination, and dispatch systems that operate at the site level — deciding where trucks go, when they go, and how they interact with each other.
Motion planning — A robust stack, from path planning to trajectory optimization, to generate smooth and safe trajectories for 200+ ton trucks to follow.
Coordination planning — Systems to simultaneously coordinate the motion of multiple vehicles with intersecting trajectories to avoid collision and maximize throughput.
Fleet planning — Algorithms that dynamically translate the site-wide state, like loading and dumping locations, to actively managed assignments for each truck.
Design and implement motion planning algorithms for non-holonomic vehicles
Develop multi-agent coordination systems that prevent deadlocks and collisions
Build simulation and visualization tools for validating planning algorithms
Optimize planning algorithms for real-time performance in production environments
Collaborate with controls engineers to ensure planned paths are executable
Debug fleet-level issues using logged data and replay tools
Travel note: This role requires periodic travel to customer sites (up to 5%)
Schedule note: Some schedule flexibility may be required during deployments
Qualification
BS/MS/PhD in RoboticsKnowledge of GEOSFamiliarity with Redis
Required
BS/MS/PhD in Robotics, Computer Science, or related field required
2+ years of professional (non-internship) software development experience
Strong foundation in motion planning algorithms
Experience with computational geometry (collision detection, polygon operations)
Proficiency in Python and NumPy for numerical computing
Understanding of vehicle kinematics and nonholonomic constraints
Ability to analyze algorithm complexity and optimize for real-time performance
Preferred
Experience with multi-agent coordination or scheduling algorithms
Familiarity with Dubins/Reeds-Shepp curves for non-holonomic planning
Background in trajectory optimization (DCBF, MPC-based planners)
Experience with graph algorithms (Dijkstra, heuristic search)
Knowledge of GEOS, Shapely or other computational geometry libraries
Experience with fleet management or dispatch systems
Familiarity with Redis, ZeroMQ, or similar infrastructure
Familiarity with modern ML techniques for planning problems
