Hiring nowRobot learning and manipulation

Robot Manipulation Researcher

Also called Manipulation Scientist

A Robot Manipulation Researcher builds the grasping and object-interaction methods that let robots handle real things reliably. They turn lab demos into systems that cope with unfamiliar objects, which is what makes a robot product usable.

What they do

They design and train methods for grasping, placing and handling objects, then test them in simulation and on real hardware. A normal week mixes reading failure logs, adjusting contact models, tuning planners and running trials on the robot. They work with perception to estimate object pose and shape, and with control to keep motion stable during contact. They build test sets that vary objects, lighting, surfaces and clutter. They decide when a simulated result is trustworthy and when it needs real-world proof. They write down what failed and why.

What a strong hire delivers

In the first months, a strong hire gives the team a working manipulation system with clear coverage: which objects, which conditions, and where it breaks. They set up an evaluation routine that measures success on unseen objects and how often the robot recovers safely from errors. They close the gap between simulation and hardware on at least one real task, and leave the team with a clear plan for what to improve next.

How you can tell they are good

Ask them to walk through a manipulation system they built and show real hardware results, including failures. Good candidates explain why a grasp failed in terms of contact, friction, pose error or planning, not just that the model was weak. They can describe how they tested on objects the system had never seen. Be wary of polished simulation videos with no real-world trial data.

Why it is hard to fill

The title varies between employers, so searching by it misses people. Candidates tend to be strong in one area, such as learning, control or mechanical design, and few are comfortable in all of them. Contact dynamics and planning knowledge sits with a small group, and many of them are in academic labs or already placed. Hands-on hardware experience is the filter that removes most applicants.

Where to find them

Look in robotics research groups, university labs moving into industry, and teams building warehouse, lab automation, household and industrial robots. Titles include Manipulation Scientist, Robotics Research Engineer, Controls Engineer and Robot Learning Researcher. Backgrounds run through robotics, control, mechanical or electrical engineering and machine learning. Frontier labs and robotics start-ups also hold people with the right mix.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for a Robot Manipulation Researcher

  1. Tell me about a grasping or manipulation system you took from simulation to a real robot. What changed?

    Look for specific differences found on hardware: friction, sensor noise, calibration, latency or contact modelling. They should say what they changed and how they checked it worked. Worry if they claim the transfer was easy or never ran real trials.

  2. How do you test that a manipulation method works on objects it has not seen?

    A strong answer covers held-out object sets, variation in shape, weight, texture and placement, and honest reporting of failures. They should avoid tuning on the test objects. Worry about small test sets or one average success figure that hides failure types.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are building robots that handle real objects in unpredictable settings. We are looking for a Robot Manipulation Researcher to develop grasping and object-interaction methods, test them in simulation and on hardware, and help turn them into a system our customers can rely on.

What you will do

  • Develop and improve grasping and object-interaction methods
  • Train and evaluate learned and planning-based manipulation approaches
  • Validate simulation results on real robot hardware
  • Build test sets covering varied objects and conditions
  • Design safe recovery behaviour for failed grasps and unexpected contact
  • Work with perception and control engineers to improve the full pipeline
  • Document failures, results and next steps clearly

What you will bring

  • Demonstrated manipulation work on real robot hardware
  • Strong understanding of contact dynamics and manipulation planning
  • Experience with reinforcement learning or other learned control methods
  • Practical computer vision experience for object pose and shape
  • Experience with ROS and motion-planning software
  • Evidence of testing on unseen objects and reporting failures honestly

Nice to have

  • Experience building simulation and digital twin environments
  • Published or shared manipulation research or open-source work
  • Mechanical or gripper design experience

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Robotics and controlAdvancedPerceive, plan and act through physical systems
  • Reinforcement learningAdvancedOptimise policies from interaction and reward
  • Simulation and digital twinsWorkingBuild useful virtual representations of environments
  • Computer visionWorkingAnalyse or generate visual information

Other roles in robot learning and manipulation

Hiring nowRobot Learning EngineerA Robot Learning Engineer trains policies that let robots complete defined physical tasks reliably. The work turns a promising demo into behaviour a…EmergingVision-Language-Action ResearcherA Vision-Language-Action Researcher builds models that turn instructions and camera input into safe, bounded robot actions. They matter because they…

Related roles in other families

Hiring nowAutonomy Perception EngineerAutonomous navigation and field roboticsAn Autonomy Perception Engineer turns raw sensor data into a reliable picture of the world that a machine can act on. It decides whether an…Hiring nowLocalisation and Mapping EngineerAutonomous navigation and field roboticsA Localisation and Mapping Engineer builds the system that tells a robot or vehicle where it is and what surrounds it. Without that, nothing…Hiring nowMotion Planning EngineerAutonomous navigation and field roboticsA motion planning engineer designs the software that decides how a robot or vehicle moves, so it reaches its goal without breaking physical limits…Hiring nowField Robotics Integration EngineerAutonomous navigation and field roboticsA Field Robotics Integration Engineer gets autonomy software and sensors working together on a real machine outdoors. It matters because autonomy…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← Robot learning and manipulationAll new job families

Start a search

Hiring a Robot Manipulation Researcher?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.