CY Cergy Paris Université
5 days ago
Postdoc in AI alignment and robotics CY Cergy Paris University in France
Degree Level
Postdoc
Field of study
Computer Science
Funding
Available
Deadline
Oct 31, 2026
Country
France
University
CY Cergy Paris Université
How do I apply for this?
Sign in for free to reveal details, requirements, and source links.
More information can be found here
Keywords
Suggested positions
About this position
CY Cergy Paris University is recruiting a postdoctoral researcher for a 12-month position in the AlFARo – Alignment Faking in AGI Robots project at the ETIS laboratory. The postdoc is based in Cergy-Pontoise, France, within an interdisciplinary environment spanning AI, robotics, cognitive science, human–AI interaction, and social robotics.
The project addresses an emerging issue in modern AI: alignment-faking, where large language models may appear compliant in training or evaluation while behaving differently when incentives or operational conditions change. Although this phenomenon has been discussed in text-based AI systems, it is still largely unexplored in robotics, especially as LLMs are increasingly integrated into robotic agents for planning and decision-making. In embodied settings, misalignment can affect physical actions and human safety.
This postdoctoral role focuses on the human side of these interactions. The successful candidate will investigate how alignment-faking and mitigation strategies influence human decision-making, vigilance, trust, and reliance on LLM-powered robots. The work includes designing and analysing controlled human–robot interaction experiments and studying how different robot behaviours affect human evaluation and willingness to follow robot recommendations.
The position is carried out under the scientific supervision of Laura Cohen and Nicolas Spatola, in close collaboration with researchers in social robotics and human–robot interaction. The post is full-time (35 hours/week) and starts on 1 Dec 2026.
Applicants should hold a PhD or equivalent in AI, human-computer interaction, human-robot interaction, cognitive science, cognitive psychology, social psychology, or a closely related field. A strong background in experimental research on human behaviour and decision-making is expected, preferably in human-AI or human-robot interaction. Useful skills include experimental design, behavioural study implementation, quantitative analysis of behavioural and questionnaire data, and strong scientific communication skills. Fluency in written and spoken English is required.
The deadline is 31 Oct 2026 at 17:00 (Europe/Paris). Applications should be sent by email to [email protected].
Funding details
Available
What's required
PhD or equivalent in AI (LLMs), human-computer interaction, human-robot interaction, cognitive science, cognitive psychology, social psychology, or a closely related field. Applicants should have a strong background in experimental research on human behaviour and decision-making, preferably in human-AI or human-robot interaction. Expected skills include experimental design and implementation of behavioural studies with human participants, quantitative analysis of behavioural and questionnaire data, knowledge of research on human trust, reliance, acceptance, decision-making, or social cognition, the ability to design and analyse controlled human-AI or human-robot interaction experiments, strong scientific writing and communication skills, the ability to work in an interdisciplinary environment, and fluency in written and spoken English.
How to apply
Apply by email to [email protected] with your application materials. Use the subject line shown in the apply link if needed. Submit before 31 Oct 2026 at 17:00 Europe/Paris.
Ask ApplyKite AI
How do I apply for this?
Sign in for free to reveal details, requirements, and source links.