Postdoc: Gesture Generation in Face-to-Face Dialogue

We are looking for a postdoctoral researcher with experience in generative AI, multimodal representation learning, and modelling face-to-face dialogues for our NWO-funded project “Grounded Gesture Generation in Context: Object- and Interaction-Aware Generative AI Models of Language Use”. Preferred start date is 1 February 2026 but is negotiable.

Face-to-face conversation is the primary setting for human language, where meaning and coordination arise from the interplay between speech, prosody, gesture, facial expression, and gaze. Virtual humans are now prevalent in social media, education, and healthcare. However, their non-verbal behaviour, especially gestures, still lags behind state-of-the-art. This project tackles that gap by building generative AI models that produce context-aware, grounded gestures: responsive to objects and to interlocutors, aligning speech and visual signals for richer, more natural interaction. In this project, you will carry out research as described in the project proposal, which includes:

• Developing generative models that produce gestures grounded in context, e.g., reacting to a partner’s gesture, resembling an object they refer to in the environment.
• Exploring how these models can enhance human-computer interaction and improve our understanding of multimodal communication.

To do so, you will have full access to motion-capture and virtual-reality labs, 3D animation tools, and GPU-based high-performance computing at MPI. You will also be embedded in a rich theoretical and computational environment supported by the Multimodal Language Department.

Requirements
Essentials

• PhD (completed or near completion) in Computer Science, Computer Vision, NLP, Machine Learning, Computer Graphics/Animation, HCI, or a related field.
• Strong background in deep generative modelling (diffusion/transformers), multimodal representation learning, and experience in computer graphics/animation.
• Strong programming skills, especially in Python. Ideally, you have experience with PyTorch.
• Track record of publishing in top Vision/Graphics/Animation and Human-Computer Interaction conferences/journals such as CVPR, ICCV, ICMI, SIGGRAPH, or similar conferences/journals.
• Strong communicative skills in English, both in writing and speech.

Desirable

• Comfortable with prototyping experiments using motion capture and virtual reality devices, 3D animation software, and relevant programming languages (e.g., Unreal Engine, Maya, Motion Builder) and with human participants.
• A strong interest in conducting research in the area of multimodal language production and visual communicative behaviours of 3D virtual humans (i.e., gesture, eye gaze, face).
• Good critical thinking and collaboration skills.

What We Offer You
A challenging position in a scientifically engaged organisation. At the MPI, you contribute to fundamental research. In return for your efforts, we offer you:

• A position for 0.8 FTE. Your employment contract will initially last 1 year. Extension might be possible depending on new funding or candidate performance. A higher FTE employment is possible, but it shortens the time of employment.
• Access to cutting-edge computing and animation facilities and a supportive, interdisciplinary team.
• Structured support for your next career steps, whether in academia or industry. For example, the successful candidate will receive help and support for securing follow-up funding (e.g., Veni/NWO XS grants, etc.) or for moving to the next career stage.
• Flexible working conditions: hybrid work, collaborative culture.
• Salary is in accordance with the German collective labour agreement TVöD (Tarifvertrag für den öffentlichen Dienst) and is classified in salary group E13.
• Pension scheme.
• Thirty days of leave per year (full-time employment).

Application Procedure
Do you recognise yourself in the job profile? Then we look forward to receiving your application. The deadline to submit your application is Friday, 14 November 2025, 23:59 (Amsterdam time). You can apply online via the apply button. Applications should include the following information:

• A one-page motivation letter, explaining why you are a good fit for this position and including a link to a publication that is relevant to the current project.
• A CV, including a list of publications, and a link to your PhD thesis.
• Contact details of two people who could be asked for recommendation letters.

About the Project
This project will be advised by Dr. Esam Ghaleb, who is a research scientist in the Multimodal Language Department in the area of computer vision, machine learning, and behaviour & dialogue modelling. If you have questions about the position you wish to discuss before applying, please contact Esam Ghaleb: esam.ghaleb@mpi.nl.

The Employer
About Our Institute
The Max Planck Institute (MPI) for Psycholinguistics is a world-leading research institute devoted to interdisciplinary studies of the science of language and communication, including departments on genetics, psychology, development, neurobiology, and multimodality of these fundamental human abilities. We investigate how children and adults acquire their language(s), how speaking and listening happen in real-time, how the brain processes language, how the human genome contributes to building a language-ready brain, how multiple modalities (as in speech, gesture, and sign) shape language and its use in diverse languages and how language is related to cognition and culture, and shaped by evolution.

We are part of the Max Planck Society, an independent non-governmental association of German-funded research institutes dedicated to fundamental research in the natural sciences, life sciences, social sciences, and the humanities.

The Max Planck Society is an equal opportunities employer. We recognize the positive value of diversity and inclusion, promote equity, and challenge discrimination. We aim to provide a working environment with room for differences, where everyone feels a sense of belonging. Therefore, we welcome applications from all suitably qualified candidates.

Our institute is situated on the campus of the Radboud University and has close collaborative links with the Donders Institute for Brain, Cognition and Behavior and the Centre for Language Studies at the Radboud University. We also work closely with other child development researchers as part of the Baby & Child Research Center. Staff and students at the MPI have access to state-of-the-art research and training facilities.

About the Multimodal Language Department
The Multimodal Language Department in particular aims to understand the cognitive and social foundations of the human ability for language and its evolution by focusing on its multimodal aspect and crosslinguistic diversity. The research at the department combines multiple methods including corpus and computational linguistics, psycho- and neuro-linguistics, machine learning, AI and virtual reality, and is concerned with various populations ranging from speakers of signed and spoken languages, young and older subjects from typical and atypical populations. The department provides opportunities for training in a range of linguistic, and conversational state-of-the-art multimodal language analysis (such as motion capture and automatic speech recognition), as well as neuropsychological, psychological methods related to multimodal language and frequent research and public engagement meetings, and support from an excellent team of researchers in linguistics and psycholinguistics.