As an intern, you join the core DL team and contribute at one or both layers of our training stack:

1. Pretraining — learn generalizable representations on large, de‑identified datasets.

2. Fine‑tuning — adapt those representations (and VLMs) to clinical tasks and ship improvements.

Work is prioritized by expected product and clinical impact; research is a means to that end.

Where you’ll contribute

Pretraining (images ± text)
Design and scale representation learning for 2D/3D medical imaging:

• Objectives: masked image modeling, self‑distillation/contrastive (MAE/DINO‑style), vision–language alignment (CLIP‑style with radiology reports).

• Modalities/architectures: X‑ray, CT, occasional MRI; 2D/3D ViTs and UNet‑style decoders.

• Systems: high‑throughput DICOM loaders, strong augmentations, mixed‑precision, distributed training.

• Evaluation: transfer to target tasks, label‑efficiency curves, robustness across sites/vendors.

Fine‑tuning (product models & VLMs)
Adapt and optimize models that power our products and workflows:

• Core tasks: detection/segmentation/registration; follow‑up (temporal matching, lesion tracking, measurements); calibration & uncertainty.

• VLMs: image encoder → decoder LLM for report generation/summarization/structured extraction. Techniques include supervised fine‑tuning on paired image–report data, instruction tuning, alignment of visual tokens (e.g., resamplers/Q‑Former‑style adapters), and LoRA/PEFT on both vision and language components.

• Efficiency & deployment: distillation, pruning/quantization, KV‑cache and batching for throughput; ONNX/TensorRT inference.

• Evaluation: AUROC/FROC/Dice, ECE calibration; for VLMs—finding‑level label agreement, RadGraph‑style entity/relational metrics, factuality checks vs imaging labels; clinician review.

You’ll spend time where it moves metrics most. Some interns focus on pretraining, others on fine‑tuning/VLMs; many touch both.

How we work (engineering standards)

• Reproducibility: Hydra configs, seeded runs, model registry; tracked experiments.

• Production‑ready code: typed Python, tests on data/metrics, documented PRs, code review.

• Measured progress: clear win criteria on accuracy, generalization, latency, and memory.

Our stack

PyTorch (Lightning), MONAI, timm/Hugging Face; NumPy/scikit‑image; DICOM tooling; W&ClearML/DVC; multi‑GPU training; ONNX/TensorRT for inference; containerized services.

• Strong ML fundamentals (probability, linear algebra, optimization).

• Proficient Python + PyTorch; experience training/debugging deep nets.

• Familiarity with self‑supervised learning and/or vision‑language models.

• Clear communication and disciplined experimentation.

• Strong drive towards improving healthcare worldwide

Nice to have: medical imaging (X‑ray/CT/MRI), 3D vision, detection/segmentation/registration, domain adaptation/uncertainty, CUDA/performance work, meaningful OSS or papers.