AI Research Scientist

WHAT WE DO

Better breast cancer screening should be a universal offering to every woman in the world. Vara’s AI-powered software platform, created with screening radiologists in Germany, mitigates much of the human subjectivity associated with reading mammography results—and reduces the repetitive work screening physicians are routinely subjected to—we’re making breast cancer screening more effective, more measurable, and more accessible for everyone, everywhere. By democratizing access to early screening around the world, we deliver measurable impact backed by clinical evidence. We are partnering globally, to deliver breast cancer screening where it is needed most.

As the first company from Europe’s leading AI venture studio Merantix, Vara has grown since 2018 to become a 50-member international team. Our diverse team consists of highly motivated and ambitious entrepreneurs, healthcare professionals, and technology experts. 

Further information can be found on our website: www.vara.ai

YOUR ROLE

The machine learning team at Vara researches, develops and productionizes high-performance AI models for breast cancer detection from mammography images. This requires solving a multi-view perception problem with an emphasis on AI safety to meet very high performance requirements.

Building on prior work to recognise trustworthy predictions [1], Vara has built a system that surpasses the metrics of individual radiologists via human-AI collaboration [2], and recognises cancers missed by humans enabling earlier detection [3]. With large-scale, prospective testing of the impact on screening system metrics [4], Vara is the established market leader in one of the most advanced public screening systems in the world and has deployed more than a million AI-assisted radiology reads.

Despite clinical metrics being improved by AI in today’s clinical practice already, we aim for perfection and continue to work towards fundamental solutions of AI for healthcare without drawing boundaries between research and engineering.

Exemplary responsibilities:

• Research, train, evaluate and certify AI models for detecting breast cancer, pushing beyond the published SOTA.
• Merge medical insights with AI to tailor our models for global needs
• Validate AI efficacy across diverse datasets, ensuring robust performance.
• Develop quantitative methods for automated monitoring of models in production.
• Work with a talented team towards breakthroughs in healthcare AI.

YOUR PROFILE

• PhD in Computer Science/Physics/Maths or equivalent practical experience, with a focus on AI/ML.
• A track record of research in ML or applied ML, ideally to medical images.
• Profound knowledge of deep learning (especially CNNs and Transformers) in theory and practice.
• Experience with real world, large scale datasets.
• Fluent engineering (Python, PyTorch/TensorFlow/Jax, GCP/AWS/Azure, software development best practices)
• Passion for good scientific practice, blending clean formal thinking with exacting engineering.

WHAT WE OFFER

• Work flexibly
  In-office? From home? Somewhere in between? Whatever you prefer.
• Team Culture
  We host regular team nights and events to foster company culture and cohesion.
• Connect at our AI Campus
  Integration into the thriving AI startup and ML community via paper reading groups, weekly lunches, and events at the AI Campus as well as conferences.
• Competitive salary
  We regularly benchmark salaries within the tech and healthcare industry.
• Develop your career
  Dedicate yourself to impactful projects and have regular, meaningful career development sessions with your manager.

ABOUT US

We are an equal-opportunity employer that values diversity. We consider all applications equally, regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, or gender identity. We strongly encourage individuals from groups that are traditionally underrepresented in tech to apply. 
Additionally, we provide immigration assistance for those who need it.