Robotics Planning Engineer

About the Role

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.

What You'll Build

• 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.

Responsibilities

• 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

Required Qualifications

• BS/MS/PhD in Robotics, Computer Science, or related field
• 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 Qualifications

• 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

Technical Environment

• Languages: Python (primary), C++ (performance-critical modules)
• Libraries: NumPy, Shapely, Numba, SciPy
• Testing: Simulation replay, config-driven scenario testing

Example Projects

• Design an intersection management system that computes optimal truck sequencing to minimize total wait time while preventing collisions
• Build a dispatch algorithm that assigns trucks to dump locations balancing load distribution and travel distance
• Develop zone-based path constraints that automatically route trucks around dynamic obstacles like active loading areas
• Create a trajectory smoother that converts piecewise-linear A* output into curvature-continuous paths suitable for MPC tracking

Pronto is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status.