Valar Labs is a well funded, fast-growing AI diagnostics startup backed by leading VCs revolutionizing oncology and urology through cutting-edge technology and innovation. We are dedicated to improving patient outcomes through the development and deployment of novel AI-driven diagnostics to reduce treatment uncertainty for oncologists and patients. Our team comprises accomplished researchers, and passionate individuals committed to shaping the future of healthcare.
Full-stack ML Engineers at Valar Labs work at the intersection of machine learning research and software engineering. They take a model from an experiment to a product that oncologists use every day, and they own the systems that keep it running.
Key Responsibilities:
Run fine-tuning and post-training experiments on our pathology and clinical models, from hypothesis to result
Build the data loops that turn clinical and lab data into curated training and evaluation sets
Develop survival and outcome models alongside medical oncologists on clinically relevant questions
Deploy models into production and own their serving, monitoring and evaluation in a HIPAA environment
Ship full stack features across our clinician portal, revenue cycle product and lab operations tooling
Build agentic AI workflows that automate clinical and operational work, with the evals that make them trustworthy
Qualifications:
Bachelor’s or Master’s degree in Computer Science, Machine Learning or a related field, or equivalent practical experience
Hands-on experience training and evaluating deep learning models in PyTorch
Strong software engineering fundamentals and production experience, ideally with TypeScript, React, Node, Docker and AWS
Genuine interest in both halves of the role: research depth and shipping products to real users
Strong interest in deploying AI in healthcare, and in seeing it change how patients are treated
Daily fluency with agentic coding tools such as Claude Code and Codex
1-4 years of experience; exceptional new grads welcome
(Optional) Publications in medical AI or machine learning venues
(Optional) Experience with pathology, medical imaging or clinical data