Epsilon Health
Research Engineer / Research Scientist, Vision-Language Model Pretraining
- Confirmed live in the last 24 hours
- No salary listed
- Mid level
- Full-time
- On-site · San Francisco, CA
- Added 1 month ago
About this role
Epsilon Health is seeking a skilled Research Scientist to advance vision-language models for medical imaging. You will own the pretraining of multimodal foundation models, focusing on architectures and training methods that enable AI to understand complex images and generate accurate radiology reports. This role offers a unique opportunity to directly impact patient care by bridging research and clinical practice.
What you'll do
- Design, pretrain, and scale vision-language foundation models.
- Invent new architectures for vision-language fusion and image understanding.
- Develop multimodal training objectives and scaling strategies.
- Improve visual grounding of medical findings within images.
- Oversee research from experimentation to large-scale training and evaluation.
- Define and implement rigorous evaluations for model performance.
What they're looking for
- Vision-language models
- Multimodal learning
- Large-scale foundation model pretraining
- PyTorch or JAX
- Distributed training
- Machine learning
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Epsilon Health
- Industry
- Technology & Software
Likely interview questions
- Describe your experience with vision-language models and large-scale pretraining.
- How do you approach designing new multimodal training objectives?