jobapplier

PhD Researcher – Video Understanding & VLMs

Almetra

Skills

Required

  • video / multimodal models
  • Machine Learning
  • AI
  • computer vision / multimodal learning
  • PyTorch

Preferred

  • vision-language / video understanding
  • VLMs
  • open VLMs
  • Qwen-VL
  • InternVL
  • LLaVA
  • video models
  • VideoMAE
  • ViViT
  • GPU clusters

About Almetra

You’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.

About Almetra

We 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.

Responsibilities

  • Video 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

Requirements

  • Master’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

Preferred

  • First publications or a strong thesis in vision-language, video understanding or multimodal learning
  • Experience with open VLMs (e.g. Qwen-VL, InternVL, LLaVA) or video models (e.g. VideoMAE, ViViT)
  • Training on GPU clusters (DDP / FSDP)
  • Why a PhD with us

A full-time, paid PhD position in Berlin

  • Mentoring from our Head of ML plus academic co-supervision
  • Unique real-world video data and the compute to use it
  • Your research reaches a real product, not just a paper

Benefits

Employee Share Options Program for all permanent employees*

  • An increasing benefits list: currently includes Urban Sports club and quarterly team retreats.
  • Be on the forefront in defining what artificial intelligence means in manufacturing
  • Gain hands-on experience in working in an AI-first software company
  • Supportive and inclusive culture that values diversity and promotes the advancement of underrepresented groups within the company
  • Collaborate with a diverse (currently more than 10 nationalities) and talented team, working on cutting-edge projects with real-world impact
  • Network with professionals and leaders in the field, opening doors to potential future career opportunities
  • We have a very flat hierarchy, open 360° feedback, and flexible working hours
  • Ethics⚖: We are committed to developing ethical AI software

Don't meet all the requirements?

Almetra is committed to creating a workplace that is diverse, fair, and inclusive. We encourage candidates from all backgrounds, even if they do not meet every qualification, to submit their application. We firmly believe that having a team with diverse perspectives only strengthens our company and drives innovation. Our commitment also extends to providing an accessible environment for everyone, including those with disabilities. Please let us know if you require any accommodations during the application process or while working with us, and we will do our best to support you.

Misc

  • *Only full-time, permanent roles are eligible for stock options. Part-time roles, contract roles, work-student, internships and freelance roles are not eligible for stock options.
  • Please apply directly. Applications sent through automated or mass-application tools are reviewed and declined, but you’re welcome to reapply here yourself.
Easy Apply