Research Scientist/ Engineer - Diffusion Policies for Robotic Learning Our client is a well-funded world model lab building generative, interactive environments that other companies build on top of. They're focused on making world models physically grounded and reliable in specific domains, where passive video data isn't enough.
This role uses robotics-style policy learning to generate the action-conditioned data that trains those world models. The work is about manufacturing training signal through control, not deploying robots in production. (This is a research role feeding world models, not a robotics product role.)
What you'll work on
Training diffusion and flow-matching policies to generate action-conditioned interaction data for world models
Building systems that collect data through control to cover dynamics that scraped video can't reach
Designing training objectives and evaluation metrics for data quality and world model improvement
Running experiments end-to-end (data collection - training - evaluation) on real manipulation hardware
What we're looking for
Strong robot learning background: imitation learning, RL, or both, on real manipulation
Hands‑on experience with diffusion policies, flow matching, or related generative approaches to control
Experience with world models, video generation, or action-conditioned prediction
Ability to run experiments end-to-end and iterate quickly
Bonus
Publications or open-source contributions in robot learning, RL, or generative modelling
Experience with large-scale or distributed model training
Dexterous or bimanual manipulation experience
Our client is an equal opportunity employer and welcomes applicants from all backgrounds. All qualified candidates will receive consideration for employment without regard to race, colour, religion, sex, sexual orientation, gender identity, national origin, disability, or veteran status.
#J-18808-Ljbffr
This role uses robotics-style policy learning to generate the action-conditioned data that trains those world models. The work is about manufacturing training signal through control, not deploying robots in production. (This is a research role feeding world models, not a robotics product role.)
What you'll work on
Training diffusion and flow-matching policies to generate action-conditioned interaction data for world models
Building systems that collect data through control to cover dynamics that scraped video can't reach
Designing training objectives and evaluation metrics for data quality and world model improvement
Running experiments end-to-end (data collection - training - evaluation) on real manipulation hardware
What we're looking for
Strong robot learning background: imitation learning, RL, or both, on real manipulation
Hands‑on experience with diffusion policies, flow matching, or related generative approaches to control
Experience with world models, video generation, or action-conditioned prediction
Ability to run experiments end-to-end and iterate quickly
Bonus
Publications or open-source contributions in robot learning, RL, or generative modelling
Experience with large-scale or distributed model training
Dexterous or bimanual manipulation experience
Our client is an equal opportunity employer and welcomes applicants from all backgrounds. All qualified candidates will receive consideration for employment without regard to race, colour, religion, sex, sexual orientation, gender identity, national origin, disability, or veteran status.
#J-18808-Ljbffr
Research Scientist/ Research Engineer Arbeitgeber: This is Growth
Growth ist ein hervorragender Arbeitgeber, der eine inspirierende Arbeitsumgebung in Zürich bietet, wo Innovation und Teamarbeit im Mittelpunkt stehen. Unsere Mitarbeiter profitieren von umfangreichen Entwicklungsmöglichkeiten, einem unterstützenden Team und einer Kultur, die Vielfalt und Inklusion fördert. Bei uns haben Sie die Chance, an spannenden Projekten im Bereich der Robotik zu arbeiten und Ihre Fähigkeiten in einem dynamischen Umfeld weiterzuentwickeln.
