Member of Technical Staff — Vision-Language Models

The Role

• 5C is building vision-language models for radiology - multimodal models that read CT, MRI, and X-ray studies and produce clinical language: findings, impressions, and structured report content a radiologist can verify and sign. This role owns that model behaviour, end to end, in production.
• We are hiring a Member of Technical Staff - Vision-Language Models. The work spans adapting and training VLMs on imaging-report data, grounding generated language in image evidence, evaluating output against clinical ground truth, and running the agent harnesses that carry these models into daily reporting.
• We are an applied AI team, not a research lab. Your output is model behaviour that holds up against radiologist-adjudicated ground truth, measured continuously, in production. Papers are a side-effect of the work, not the work.
• We are strongly biased toward candidates who can join quickly. If your notice period is short, your application will move faster because these teams are being built now.

What You Will Build

• Vision-language models for radiology: adapting open and frontier multimodal architectures to imaging-report data, from fine-tuning through preference optimisation on real radiologist edits
• Grounding systems that tie every generated clinical statement to image evidence - localisation, slice and region attribution, and explicit uncertainty when the evidence is weak
• Evaluation against clinical ground truth: benchmark suites built with our radiologists, regression catches across model versions, calibration surfaces, and error taxonomies that separate harmless phrasing drift from clinical error
• Agent harnesses in production: orchestration, tool integration, structured state passing, retry and fallback logic, deterministic replay, and cost / latency governors around the models you ship
• Data pipelines across DICOM studies, reports, annotations, and radiologist feedback that turn daily reporting into training and evaluation signal
• Tight loops with the computer vision team and the radiologists who define ground truth. The model is only as good as the evaluation it answers to

You Should Have

• 2+ years of hands-on experience training, adapting, or productionising multimodal or large language models - not just calling APIs from a notebook
• Strong Python and PyTorch, including custom datasets, training loops, distributed training or inference, and serious debugging instincts
• An eval-first mindset: you instinctively reach for reproducible measurement against ground truth before changing a model, a prompt, or a dataset
• Experience with at least one of: vision-language architectures (contrastive, LLaVA-style, or natively multimodal), image-conditioned generation, grounding and localisation, RLHF / preference optimisation, or clinical NLP
• Clear thinking about how a generative model fails in a clinical setting: hallucinated findings, false reassurance, laterality errors, silent regressions

Even Better If You Have

• Publications, strong research artifacts, or open-source contributions in multimodal ML or medical AI
• Experience with medical imaging data: DICOM, 3D volumes, radiology reports, or clinical annotation workflows
• Built evaluation harnesses, tracing, or trajectory tooling for LLM or agent systems running in production
• Worked with clinicians to define ground truth in a high-stakes domain

Why 5C

• 5C is one of the best places to work for serious, engaged builders. We are a leading company in agent-driven software development and a leading business in AI for medical imaging at the same time
• You will work on systems that move from code to clinical impact unusually quickly: reports delivered faster, radiologists made more effective, hospitals able to serve more patients
• Resumes are not important. Proof of work and proof of a high learning rate matter more. Show us systems you built, products you shipped, open-source work, customer outcomes, or unusually strong side projects
• We are strongly biased toward candidates who can join quickly. If your notice period is short, your application will move faster because these teams are being built now.