Two Postdoctoral Positions in Robot Learning and Embodied AI
Pubblicato il 13-08-2026 - The Italian Institute of Artificial Intelligence (AI4I) in Torino
AI4I — Italian Institute of Artificial Intelligence, Turin
Location
Duration
2 years, renewable
Preferred November 2026; flexible
Compensation
(Researchers relocating from abroad may be eligible for tax exemptions of up to 90%. link)
Deadline
September 30, 2026 — applications reviewed on a rolling basis until filled
The Machine Intelligence for Robot Autonomy (MIRA) Laboratory at the Italian Institute of Artificial Intelligence (AI4I), is seeking two Postdoctoral Researchers in Robot Learning and Embodied AI.
Our goal at MIRA is to develop the algorithmic foundations and system-level methodologies that enable AI-powered autonomous systems to operate safely, efficiently, and reliably in high-stakes environments. Our work addresses these challenges by employing and advancing techniques from AI/ML, statistical learning, control theory, and mathematical optimization, and we apply the results to aerospace robotics, future mobility systems, and autonomy at large.
Ultimately, the goal of our lab is to push the boundaries of autonomy in high-stakes, safety-critical domains.
These environments force existing methods to operate at the edge of what is currently possible, accelerating the next generation of autonomous systems: "a wind tunnel for Physical AI".
We are looking for researchers who want to tackle ambitious problems in AI and autonomy, with strong technical foundations, clear scientific taste, and the ambition to define and lead new research directions.
Research
Successful Candidates Will Have The Freedom And Support To Shape Their Research Agenda Within The Broader Scientific Direction Of MIRA. Topics Of Interest Include
- Foundation models for autonomy, including LLMs, VLMs, and VLAs
- Reinforcement Learning and Imitation Learning
- Physical AI safety
- Continual learning, generalization under distribution shift, and real-time adaptation
- Integration of learning with optimal control and model-based methods
- Decision-making for large-scale, coordinat