Robotics Technologist III: Stochastic Planning and Control for Field Robotics

JPL

$149K — $186K *
Aerospace & Defense
5 - 7 years of experience
Job Overview by Ladders

Qualifications

  • Bachelor's degree in Computer Science, Mechatronics Engineering, or related field (6+ years experience); Master's (4+ years); or Ph.D. (2+ years) required.
  • Experience in developing uncertainty-aware motion planning and control systems.
  • Expertise in estimation theory, simultaneous localization and mapping, and sensor fusion.
  • Proficiency in multi-agent planning and POMDP frameworks.
  • Strong programming skills in Python, C, and C++.
  • Experience with robot software stacks using ROS2.
  • Hands-on experience with hardware integration for robotic field operations.

Responsibilities

  • Design and implement constraint-aware motion planning and controls for multi-agent systems.
  • Apply deep learning for perception-aware stochastic planning.
  • Develop low-level algorithms using model predictive control, reinforcement learning, and various planning approaches.
  • Create high-level planning frameworks using POMDP and Monte Carlo Tree Search for action selection.
  • Conduct robust integration with existing ROS2-based robot software stacks.
  • Support field trials to evaluate the autonomous navigation capabilities of robotic systems.

Benefits

  • Comprehensive health, dental, and vision plans.
  • Wellbeing and retirement plans.
  • Paid time off.
  • Childcare and flexible scheduling options.
  • Parental leave support.
  • Focus on work-life balance with a health-conscious mentality.
Full Job Description
Wanted: A Robotics Technologist III with advanced skills in motion control, planning, state estimation, and machine learning, as they apply to robotic systems for the Robotic Surface Mobility Group, which is part of the Robotic Mobility and Manipulation Section.

The Robotics section develops, matures, and brings to space flight, robotics technology for in-situ exploration of the solar system. The Section also provides robotics expertise for space flight hardware and software implementation along with mission operations support.

Opportunity: To work with an enthusiastic multi-disciplinary workforce that originates and executes robotics technology development and space flight projects. This role is highly focused on addressing complex motion control, planning, and state estimation challenges across various active projects. The candidate will be responsible for developing controls and planning algorithms, integrating deep learning models, and designing high-level multi-agent planning frameworks to support robotic operations.

What You'll Do

  • Design and implement constraint-aware motion planning and controls for multi-agent systems.
  • Apply deep learning for perception-aware stochastic planning.
  • Develop low-level algorithms utilizing model predictive control, reinforcement learning, and grid-based or sampling-based planning.
  • Develop higher-level planning frameworks incorporating Partially Observable Markov Decision Processes (POMDP) and action selection using Monte Carlo Tree Search.
  • Perform robust robot system integration work with the existing ROS2-based robot software stacks.
  • Support field trials to evaluate autonomous navigation of robotic systems.


Required Qualifications

  • Bachelor's degree in Computer Science, Mechatronics Engineering, or a related discipline with a minimum of 6 years of relevant experience; a Master's degree in a related discipline with a minimum of 4 years of relevant experience; or Ph.D. in a related discipline with a minimum of 2 years of relevant experience.
  • Experience developing uncertainty-aware motion planning and control systems.
  • Demonstrated expertise in estimation theory, simultaneous localization and mapping, and sensor fusion.
  • Proficiency in multi-agent planning and POMDP decision-making frameworks.
  • Strong programming proficiency in Python, C, and C++.
  • Experience developing and operating robot software stacks using ROS2.
  • Experience operating and integrating hardware for robotic field expeditions.
  • Strong communications skills and ability to work across teams.


Desired Qualifications

  • Familiarity with simulation tools for robotic development such as Gazebo, IsaacSim, or MuJoCo.
  • Proficiency with modern machine learning frameworks (e.g., PyTorch, TensorFlow) for training and deploying perception and vision models.
  • Experience with compute optimization and GPU acceleration (e.g., CUDA, TensorRT) for real-time, onboard robotic processing.
  • Familiarity with diverse sensing modalities (e.g., LiDAR, stereo cameras, IMUs) tailored for resource-constrained or GPS-denied environments.
  • Experience in continuous integration and rigorous software testing methodologies (e.g., hardware-in-the-loop, software-in-the-loop) for autonomous operations.


Please provide contact information for three references

JPL has a catalog of benefits and perks that span from the traditional to the unique. This includes a variety of health, dental, vision, wellbeing, and retirement plans, paid time off, learning, rideshare, childcare, flexible schedule, parental leave and many more. Our focus is on work-life balance, and living healthy, fulfilling lives as we Dare Mighty Things Together. For benefits eligible positions, benefits are effective the first day of the month coincident with or immediately following the employee's start date.

For further benefits information click Benefits and Perks

The hiring range displayed below is specifically for those who will work in or reside in the location listed. In extending an offer, Jet Propulsion Laboratory considers factors including, but not limited to, the candidate's job related skills, experience, knowledge, and relevant education/training.

The typical full time equivalent annual hiring range for this job in Pasadena, California.

$149,656 - $186,888

Similar Jobs

More Jobs at JPL

More Aerospace & Defense Jobs

Find similar Robotics Technologist III: Stochastic Planning and Control for Field Robotics jobs: