Role OverviewWe're seeking a
Research Scientist with deep expertise in
Vision Language Modeling (VLMs) to join our ML team. You'll be at the forefront of developing and deploying state-of-the-art multimodal models for clinical use in radiology settings. This role focuses on training and fine-tuning vision-language models (VLMs) that can generate
accurate & grounded radiology reports across
multiple imaging modalities including X-rays, CT scans, and MRI. You'll work with one of the largest and most diverse medical imaging datasets in the industry, advancing the state-of-the-art in grounded medical report generation, model alignment, and
inference-time reasoning while maintaining the clinical rigor required for healthcare deployment.
Key Responsibilities- Design, train, and scale vision-language foundation models for radiology applications.
- Develop and implement advanced post-training strategies including preference optimization (DPO, IPO, KTO), reinforcement learning from human feedback (RLHF), and other alignment techniques to improve clinical accuracy and reduce hallucinations.
- Research and deploy inference-time compute scaling techniques such as chain-of-thought reasoning, self-refinement, and test-time training to enhance model performance on complex diagnostic cases.
- Pioneer grounded report generation capabilities, enabling models to spatially localize findings within medical images using bounding boxes or segmentation masks.
- Design rigorous evaluation frameworks that assess text for medical accuracy and writing style.
- Contribute hands-on to all stages of model development including dataset curation, architecture design, distributed training, post-training optimization, and production deployment.
- Stay current with cutting-edge research in vision-language modeling, medical AI, and model alignment techniques.
- Drive research and technical excellence through conference publications and technical blog posts, establishing best practices for training robust medical VLMs at scale.
Qualifications- 6+ years of academia/industry experience in vision-language modeling, multimodal learning, or related fields
- Deep expertise in training and fine-tuning large vision-language models (e.g., LLaVA, Flamingo, CogVLM, Qwen-VL, or similar architectures)
- Strong foundation in modern post-training techniques including:
- Preference optimization methods (DPO, IPO, ORPO, KTO)
- RLHF and reward modeling
- Inference-time compute scaling and reasoning strategies
- Constitutional AI and other alignment techniques
- Track record of implementing complex models from research papers and adapting them to new domains
- Proficiency in PyTorch or JAX, with experience training large models on multi-GPU/distributed systems
- Experience with autoregressive language modeling and instruction tuning
- Hands-on experience with medical imaging applications, particularly radiology report generation
- Strong software engineering skills and ability to write production-quality code
Preferred Qualifications- Publications at top-tier conferences (NeurIPS, ICML, ICLR, CVPR, ACL, EMNLP, MICCAI)
- Experience with grounded generation tasks (visual grounding, referring expression comprehension)
- Knowledge of evaluation methodologies for long-form generation, including factuality assessment and hallucination detection
- Experience with 3D medical image processing and temporal modeling
- Familiarity with clinical NLP and medical knowledge representation
- Experience with model interpretability, explainability, and uncertainty quantification in safety-critical applications
