VLM Research Engineer

Responsibilities

• Design and adapt vision-language and video models for scene understanding, temporal reasoning and activity / action recognition
• Build and maintain large-scale training and evaluation pipelines on GPU clusters
• Curate and augment video-text and action datasets, including synthetic labels and retrieval-based augmentation
• Develop robust benchmarks for video QA, instruction following and temporal understanding
• Cut and refactor model architectures for efficiency and deployability via compression, pruning, and distillation
• Deliver production-ready inference pipelines to product and customer teams

Requirements

• PhD or equivalent research track record in computer vision, machine learning, robotics, or a related field
• Strong background in video-centric deep learning (scene understanding, temporal/activity recognition, or video generation)
• Experience training and adapting large vision or VLM models (e.g., InternVL, Qwen-VL, DeepSeek-VL)
• Proven work with multi-GPU training using PyTorch, distributed training, and mixed precision
• Solid engineering habits with clean Python and reproducible experiments
• Track record of moving research into usable systems or productized features

Preferred Qualifications

• Publications at top-tier venues (CVPR, ICCV, ECCV, NeurIPS, ICLR) regarding video or multimodal learning
• Experience with 3D/4D scene representations or embodied AI projects
• Inference optimization experience including quantization, TensorRT, or model distillation
• Prior experience in a startup or applied research lab environment

Benefits

• Employee Share Options Program for permanent employees
• Urban Sports club membership
• Quarterly team retreats
• Flexible working hours and flat hierarchy

About the Company

Almetra is an AI-first software company focused on defining what artificial intelligence means in manufacturing through cutting-edge multimodal models.