
Master Thesis Title: Physical Recursive Self Improvement (P-RSI)
Join the Robotics and AI Institute for a master thesis focused on Recursive Self-Improvement (RSI) in robotics. This research explores how an AI system can autonomously improve its training processes through sim-to-sim and sim-to-real transfers, addressing the challenges faced in physical robotics. You'll work with a mature robotics platform and collaborate with ETH Zurich, benefiting from strong engineering support and state-of-the-art facilities. Candidates should be prepared for a competitive selection process, which includes submitting a CV and letter of motivation.
Job description
What if a robot’s training pipeline could improve itself? Today, getting a reinforcement-learning policy from simulation onto a real robot takes long, manual tuning by a few experts. Recursive self-improvement (RSI) offers a potential solution by enabling systems to optimize not only their task policies, but also the underlying algorithms and environments that generate them. While RSI has achieved success in software domains through automated code generation and unit testing, extending these mechanisms to physical robotics introduces severe challenges, including partial observability, shifting dynamics, and the high cost of real-world failures. In this thesis, you explore how an AI system can take over parts of that loop and learn from conducting frequent sim-to-sim and periodic sim-to-real transfers. Instead of tuning the pipeline for a single task, the system turns lessons from sparse real-robot trials into general training rules. It then validates and refines these rules across diverse simulated scenarios, steadily improving its own training process with minimal physical risk. Environment: The thesis is conducted at the RAI Institute, a top-notch robotics research institute with representation in Zurich. It would happen as part of a collaboration agreement between RAI and ETH Zurich. A mature robotics stack running on a multitude of robots and enabling fast testing cycles, strong engineering support, and a best-in-class robotics research laboratory with state-of-the-art computing infrastructures led by distinguished scientists in the field make this opportunity second to none. For examples of the platforms and deployments developed at the institute, please have a look at the videos on our channel Please append your CV, letter of motivation, and transcripts to the application. Selection is highly competitive. If considered, you will be invited to an on-site interview. [1] Luo, M., Bai, Z., Xu, S., et al. (2026). Toward recursive self-improvement in physical AI. arXiv. What if a robot’s training pipeline could improve itself? Today, getting a reinforcement-learning policy from simulation onto a real robot takes long, manual tuning by a few experts. Recursive self-improvement (RSI) offers a potential solution by enabling systems to optimize not only their task policies, but also the underlying algorithms and environments that generate them. While RSI has achieved success in software domains through automated code generation and unit testing, extending these mechanisms to physical robotics introduces severe challenges, including partial observability, shifting dynamics, and the high cost of real-world failures. In this thesis, you explore how an AI system can take over parts of that loop and learn from conducting frequent sim-to-sim and periodic sim-to-real transfers. Instead of tuning the pipeline for a single task, the system turns lessons from sparse real-robot trials into general training rules. It then validates and refines these rules across diverse simulated scenarios, steadily improving its own training process with minimal physical risk. Environment: The thesis is conducted at the RAI Institute, a top-notch robotics research institute with representation in Zurich. It would happen as part of a collaboration agreement between RAI and ETH Zurich. A mature robotics stack running on a multitude of robots and enabling fast testing cycles, strong engineering support, and a best-in-class robotics research laboratory with state-of-the-art computing infrastructures led by distinguished scientists in the field make this opportunity second to none. For examples of the platforms and deployments developed at the institute, please have a look at the videos on our channel Please append your CV, letter of motivation, and transcripts to the application. Selection is highly competitive. If considered, you will be invited to an on-site interview. [1] Luo, M., Bai, Z., Xu, S., et al. (2026). Toward recursive self-improvement in physical AI. arXiv.
Job details
- Published
- November 12, 2026
- Last checked
- November 17, 2026
- Job source
- lever
- Workplace
- On-site · Zurich, CH
- First seen
- November 13, 2026
LiftmyCV exclusive data
Robotics and AI Institute hiring intelligence
Robotics and AI Institute currently has 13 active jobs tracked by LiftmyCV. 12 new jobs in the past 7 days.
Verified November 17, 2026
Active openings
13
Currently tracked by LiftmyCV
New in 7 days
12
13 new jobs in the past 30 days
Published salaries
—
Not published by this employer yet
Average opening age
7 days
Across 13 active openings
Workplace breakdown
Hiring countries
Top hiring cities
Most in-demand roles
- • Applied Scientist - Agents & Robotics
- • Applied Scientist - Learning-Based Navigation and Locomotion
- • Applied Scientist – State Estimation & Integration
- • Electrical Engineering Technician
- • Finance and Accounting Analyst
- • Hardware Engineer - Electrical
Frequently requested skills
As of November 17, 2026
Hiring insights calculated from active jobs tracked by LiftmyCV.
See how well you match this job
Log in or sign up and Eva will compare your profile with this role, explain your strengths and show what to improve.
Sign up to see your matchAlready have an account? Log inMore at Robotics and AI Institute
Similar jobs from this company
Across the market
Similar jobs from other companies
- Researcher, Recursive Self-Improvement SafetyOpenAISan Francisco, USOn-site
- Staff+ Research Engineer – Recursive Self-Improvement LeadSequen AIUSRemote
- Master Thesis: Self-Improving AI for Automated AI DevelopmentSaab Dynamics ABKarlskoga, SEOn-site
- Master ThesisSAAB AktiebolagLinkoping, SEOn-site
- Master's ThesisSAAB AktiebolagGoteborg, SEOn-site
- Master's Thesis StudentDeloitteOslo, NOOn-site$4,000 per year
Related job searches
Third-party content disclaimer
Full job descriptions are sourced directly from third-party applicant tracking systems (ATS), job boards, recruitment platforms, and employer career pages.
LiftmyCV does not claim ownership of this content or guarantee its accuracy or current availability. All original content is the intellectual property of the respective employers or other rights holders.
LiftmyCV hiring intelligence, availability checks, and related-job recommendations are generated from LiftmyCV data and public sources.
If you prefer, you may apply directly via the original listing for transparency.