Description du poste
About AlmetraWe build vision-language models that understand what happens on real factory floors. Cameras on 20+ production lines stream video into our models, which turn every step (assembling, screwing, inspecting) into structured data several times per second. Customers use it to see where time gets lost and how to improve their processes.
Your roleYou’ll do your PhD with us from day one, working closely with Sascha, our Head of ML (VLM), on research problems that come straight from our product. Your research runs on real industrial video at a scale few academic labs have. The PhD is co-supervised by a university professor, and you’ll be enrolled at a partner university.
What you’ll work onVideo understanding with VLMs: action recognition, temporal grounding and long-video reasoning on factory footage
Making models robust in the real world: occlusions, unusual viewpoints, new stations and products with little labelled data
Turning research results into improvements in our production models
Publishing at top venues (CVPR, ICCV/ECCV, NeurIPS, ICLR) together with our ML team
What you bringMaster’s degree in Computer Science, Machine Learning, AI or a closely related field, with a focus on computer vision or multimodal learning (finished or finishing by early-2027)
Solid deep learning foundations and hands-on PyTorch
Experience with computer vision, video or multimodal models (thesis, projects or internships)
Curiosity about real-world problems, not only benchmarks
Fluent E