Research Engineer / Research Scientist, Vision-Language Model Pretraining

The role

You will design, pretrain, and scale vision-language foundation models for medical imaging. You will develop architectures and training methods to enable AI to understand complex medical images and generate radiology reports.

What you will do

• Design, pretrain, and scale vision-language foundation models for medical imaging.
• Explore novel approaches to vision-language fusion, high-resolution image understanding, and efficient visual token representations.
• Develop multimodal training objectives, data mixtures, and scaling strategies.
• Improve how models connect medical findings to specific regions, structures, and abnormalities within images.
• Take ideas from hypothesis and experimentation through large-scale distributed training, evaluation, and handoff to post-training.
• Develop rigorous evaluations for visual understanding, grounding, generalization, and downstream model performance.
• Publish original research and share technical insights.

Required qualifications

• Deep expertise in vision-language models, multimodal learning, or large-scale foundation model pretraining.
• Demonstrated ability to develop, train, or improve state-of-the-art machine learning models.
• Strong understanding of modern VLM architectures, multimodal training objectives, and vision-language alignment.
• Experience with large-scale distributed training using PyTorch or JAX.
• Ability to independently formulate research questions, design experiments, and turn promising ideas into working models.
• Strong engineering skills and a track record of implementing and extending ideas from research.
• A rigorous, experimental mindset and the ambition to solve difficult, unsolved problems.

Nice to have

• Publications at leading ML or computer vision conferences such as NeurIPS, ICML, ICLR, CVPR, or MICCAI.
• Experience developing or scaling models such as LLaVA, Qwen-VL, InternVL, or similar multimodal architectures.
• Experience training vision encoders or developing novel vision-language connector architectures.
• Familiarity with high-resolution imaging, visual grounding, or 3D/volumetric data.
• Experience with contrastive learning, generative pretraining, or large-scale multimodal data curation.
• Background in medical imaging, radiology, or other scientific imaging applications.
• Experience evaluating model factuality, interpretability, or reliability in high-stakes settings.

About the company

Epsilon Health is transforming medical imaging and diagnostics by bringing frontier AI into clinical practice. The research team uses proprietary medical imaging datasets to build technology that improves patient outcomes.