Medical Vision-Language Research Engineer

Alt; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Epsilon Health in San Francisco seeks a Research Scientist to push the frontier of vision-language models for medical imaging. You will own the pretraining of multimodal foundation models, developing architectures and training methods that enable AI to understand complex medical images and generate clinically accurate radiology reports.

You’ll tackle multimodal learning challenges across X-rays, CT, and MRI, drawing on real-world clinical data and collaborating with researchers and engineers to

Qualifications

• Deep expertise in vision-language models or multimodal learning.
• Ability to develop, train, or improve state-of-the-art ML models.
• Strong understanding of modern VLM architectures and vision-language alignment.
• Experience with large-scale distributed training using PyTorch or JAX.
• Independent formulation of research questions, design experiments, and turn ideas into working models.
• Strong engineering skills and a track record of implementing research concepts.
• Rigid, experimental mindset and ambition to solve difficult problems.

Responsibilities

• Advance the frontier of multimodal AI by designing, pretraining, and scaling vision-language models for medical imaging.
• Invent new architectures and explore fusion approaches for high-resolution image understanding.
• Develop multimodal training objectives and scaling strategies across image-text data.
• Improve visual grounding to relate findings to specific regions and structures in images.
• Own research end to end from hypothesis through large-scale training, evaluation, and handoff to post-training.
• Define rigorous evaluations for visual understanding and model performance.
• Publish original research and contribute to the medical AI field.

Skills

Vision-language models

Multimodal learning

Pretraining

PyTorch/JAX

Experiment design

Research leadership

Engineering skills

Job description

Epsilon Health in San Francisco seeks a Research Scientist to push the frontier of vision-language models for medical imaging. You will own the pretraining of multimodal foundation models, developing architectures and training methods that enable AI to understand complex medical images and generate clinically accurate radiology reports.

You’ll tackle multimodal learning challenges across X-rays, CT, and MRI, drawing on real-world clinical data and collaborating with researchers and engineers to