PhD Researcher – Video Understanding & VLMs
💰 $80,000 – $130,000/yrMarket estimate · not provided by the employer
At a glance
- Who can apply
- Germany
- Work arrangement
- Remote · Remote
- Employment type
- Full-time
- Salary
- $80,000 – $130,000/yr · market estimate
- ✓ Open to early-career candidates
Checked against the employer's source on November 21, 2026. Details come from the employer's posting; confirm them on the application page.
Advertisement
Put your brand in front of 300,000+ monthly visitors worldwide
Job Description
Almetra builds vision-language models that turn factory-floor camera video into structured step data for customers optimising production. This role is a full-time PhD researcher position on video understanding and VLMs, co-supervised with a university professor.
- Carry out PhD research on video understanding with VLMs, including action recognition, temporal grounding and long-video reasoning on factory footage
- Develop models that stay robust under occlusions, unusual viewpoints, and new stations or products with little labelled data
- Turn research results into improvements for Almetra's production models
- Publish research at top venues such as CVPR, ICCV/ECCV, NeurIPS and ICLR together with the ML team
- Work closely with the Head of ML (VLM) on problems that come from the product
Summary of Almetra's posting by JobsRemoteList. Read the full details and apply on the employer's site.
Requirements
- Master's degree in Computer Science, Machine Learning, AI or a closely related field, finished or finishing by early 2027
- Focus in computer vision or multimodal learning preferred
- Solid deep learning foundations and hands-on PyTorch experience
- Experience with computer vision, video or multimodal models through thesis, projects or internships
- Curiosity about real-world problems rather than only benchmarks
- Fluent English
- Nice to have: first publications or strong thesis in vision-language, video understanding or multimodal learning
- Nice to have: experience with open VLMs such as Qwen-VL, InternVL or LLaVA, or video models such as VideoMAE or ViViT
- Nice to have: training on GPU clusters using DDP or FSDP
Benefits
- Full-time, paid PhD position based in Berlin
- Mentoring from the Head of ML plus academic co-supervision
- Employee Share Options Program for permanent full-time employees
- Urban Sports Club membership and quarterly team retreats
- Flexible working hours and a flat hierarchy with open 360° feedback
Advertisement
Put your brand in front of 300,000+ monthly visitors worldwide
Related Jobs
Find more than a single listing
Discover more jobs
Join now and find your dream job or a higher-paying opportunity with better employer visibility, stronger internal discovery and easier access to worldwide hiring signals.
Discover hidden jobs
Surface roles you may miss on noisier boards and move through cleaner employer links and better intent pages.
Head start against the competition
See fresh roles, related pages, salary context and company signals faster so you can apply earlier and better.
10,000+ more jobs than narrower job boards
Explore remote, hybrid and location-based opportunities across worldwide markets instead of relying on one narrow inventory.
Worldwide opportunity coverage
Use region pages, country-eligibility pages and skill pages built for global job seekers, not just one market.
Social proof
Trusted by professionals
“There were too few vacancies in my selected category.”
Amir Hakim
Marketing Specialist · 🇲🇾 Malaysia
“The job details were clear and the application links worked smoothly.”
Ingrid Hansen
Product Manager · 🇳🇴 Norway
“I would like more frequent updates and more junior-level vacancies.”
Aino Korhonen
Recruiter · 🇫🇮 Finland