Search
Go
VLM Research Engineer (m/f/d)
Summary by AIEngineer.careers
VLM Research Engineer (m/f/d) is a AI Research Engineer role (full-time). with Almetra. in BERLIN, DE. Imported listing (source: qarera.com). Apply on the employer's site (qarera.com).
Imported listing (source: qarera.com) · Apply on qarera.com
BERLIN · DE
—
Full-time
SENIOR
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from qarera.com
Almetra is seeking a Senior AI Research Engineer to advance vision-language models for real-world video understanding and scene analysis. The role involves designing multimodal architectures, building large-scale training pipelines on GPU clusters, and deploying production-ready inference systems. Candidates must have a PhD or equivalent research track record in computer vision or machine learning.
Responsibilities
- Design and adapt vision-language and video models for scene understanding and temporal reasoning
- Build and maintain large-scale training and evaluation pipelines on GPU clusters
- Curate and augment video-text datasets with synthetic labels and retrieval-based methods
- Develop robust benchmarks for video QA and instruction following
- Optimize model architectures for efficiency via compression, pruning, and distillation
- Deliver production-ready inference pipelines to product teams
Requirements
- Completed PhD (or equivalent research track record) in computer vision, ML, robotics, or related field
- Strong background in video-centric deep learning and multimodal models
- Experience training large vision/VLM models (e.g., InternVL, Qwen-VL)
Almetra
Berlin · DE · 40+ employees
Almetra is a manufacturing intelligence company that uses privacy-preserving computer vision and AI to provide insights into manual production processes. The company helps manufacturers optimize assembly lines, identify bottlenecks, and make data-driven improvements without requiring manual studies or disruptive hardware changes.
