Research areas

Scaling laws for robot learning.
Benchmarking robot data collection methods.
Measuring robot capability and its economic reach.
Quantifying technical progress of models, algorithms and hardware over time.

These are some of the current research directions of interest and should not be read as a full and fixed list. The specific project you lead will be agreed at the start based on your strengths and the state of the work.

Principal Duties and Responsibilities (Essential Functions**)

Research

• Design, run and analyze machine learning experiments on robot learning models, including fine tuning, evaluation and ablation studies.
• Build and maintain evaluation pipelines so that results are comparable across tasks, models and runs.
• Manage training and inference workloads on MIT's high performance computing resources, including job scheduling, environment management and experiment tracking.
• Collect, clean and document datasets on robot platforms, benchmarks and capabilities, including from technical papers, product documentation and public sources.
• Keep code and results reproducible, in shared repositories with documentation sufficient for another lab member to rerun an experiment.

Analysis and reporting

• Produce research visualizations and written analysis for academic papers, public articles and reports.
• Contribute to grant proposals and other research writing.
• Prepare research documentation and track key project metrics.

Supervision and collaboration

• Co-supervise undergraduate researchers on technical project components.
• Collaborate with lab members working on the economics of automation, and with external academic and industry partners.
• Participate in lab meetings, workshops and conferences.
• Other duties as needed or required.

Supervision Received

Reports to Neil Thompson, Director of MIT FutureTech, with day to day project direction from Sebastian Sartor. Works under general oversight with direction on non-routine issues.

Supervision Exercised

May guide the work of undergraduate researchers.

Qualifications & Skills

Minimum Required Education and Experience

• BA or BS in computer science, electrical engineering, robotics, machine learning, or a related field.
• Proficiency in Python and hands on experience with a deep learning framework, in particular training or fine tuning models rather than only calling APIs.
• Experience with a physics simulator such as MuJoCo and Isaac Sim OR with real robot data collection and policy deployment.
• Comfort working on a Linux compute cluster, including job schedulers such as SLURM, environment management and debugging jobs that fail for infrastructure rather than modeling reasons.
• Ability to read and evaluate robot learning papers independently.
• Strong written and verbal communication skills in English.
• Ability to work independently and to keep work organized and documented for others.

Preferred Education and Experience

• MS in computer science, robotics or a related field.
• Direct experience with vision language action models and their training stacks.
• Experience with modern robot learning methods such as imitation learning, reinforcement learning, diffusion or flow-matching policies, or other learned approaches to action generation.
• Experience with robotics software and simulation stacks such as ROS/ROS 2, Isaac Lab, ManiSkill, robosuite or similar environments.
• Experience training or evaluating policies across multiple tasks, environments or robot embodiments, including studies of generalization and transfer.
• Experience with robot data collection hardware, teleoperation rigs or manipulator arms.
• Experience running scaling or ablation studies where the result is a fitted curve rather than a single number.
• Interest in the economic and labor market consequences of automation, and willingness to engage with occupational data even without formal training in economics.
• Prior experience supervising or mentoring undergraduate researchers.
• Research paper writing experience.

Additional information

• One-year term appointment, with potential for renewal after one year, subject to grant funding.
• Work is primarily on site at MIT FutureTech in Cambridge, MA.

How to apply

Please use this form to register interest in this role or to submit a general expression of interest.

Selected candidates will be first interviewed via Zoom. We are recruiting on a rolling basis and may close applications early if we find a suitable candidate, so please apply as soon as possible to maximize your chances.

** To comply with regulations by the American with Disabilities Act (ADA), the principal duties in position descriptions must be essential to the job. To identify essential functions, focus on the purpose and the result of the duties rather than the manner in which they are performed. The following definition applies: a job function is essential if removal of that function would fundamentally change the job.

‍