ML/DL Research Engineer

Job description

The models you help develop are at the heart of the innovation weโ€™re bringing to the dental market, to raise the international standard of healthcare

Promaton is changing dental healthcare by automating diagnostics and treatment workflows using AI, making healthcare more affordable and accessible for everyone. Did you know dentists miss up to 30%ย of pathologies on an X-Ray?ย We are on a mission to eliminate errors in dentistry by improving diagnostic accuracy, and automating mundane work like creating 3Dย models by hand from an X-Ray. See our company page to learn more about what we do.

You'll be:

  • Applying your AI expertise to positively impact the lives of dentists and their patients in the real world
  • Developing and/or improving our deep learning models, together with our clinical experts
  • Improving the quality, accuracy, and performance of our deep learning inference pipelines
  • Diving into the (dental imaging) data, looking for trends, outliers, and other factors that may influence the performance of our algorithms
  • Doing R&D projects, and even contributing to patents.

You'll be working with an accomplished team of data scientists, that already have 8 patents on their name, and created market leading algorithms that are in use throughout the world.

The challenges you'll help us overcome:

  1. Medical AI has to comply with the highest quality standards. While in other industries failing to predict for example a recommended product has little consequence, in the medical field you really don't want to be wrong. Safety-critical AI is a hard topic.
  2. We work with vast amounts of real-world data, which means having to deal with the infamous long tail (and "data desert") in cases that we cover. Being creative, and having a research experiment-and-repeat mindset here is critical.
  3. Expressing performance of algorithms in image analysis can be challenging, especially when you want to combine it with clinical performance. Communicating how well our algorithms perform (both visually and in metrics) is something we continuously improve upon.

The perks of working at Promaton:

  • ๐Ÿ’ฐ Excellent employment terms
  • ๐Ÿก Freedom to work from anywhere you like (and any time you like). We only have a few touch points.
  • ๐Ÿ‘ฉโ€๐Ÿ”ฌ Dedicated time for hackathons and research, to explore new ideas of your own. We have a quarterly "hack for a week on anything you like" and a monthly paper review sessions, where we present the latest developments in the field to each other.
  • ๐ŸŽ“ Real training budget for books and conferences or anything else you need to grow
  • ๐Ÿš€ Work with the latest technology, on the forefront of a rapidly changing field in medical imaging AI
  • ๐Ÿ’ช Loads of responsibility and autonomy (we hate micro management) and a chance to make a real impact
  • ๐Ÿ– Awesome yearly company retreat, and quarterly team events
  • โ›บ๏ธ 25 days of annual leave
  • ๐Ÿ’ป Top-notch gear, and even bigger servers to play with
  • ๐Ÿ„โ€โ™‚๏ธ Promaton is funded for many years to come, meaning you can have the impact you only get at a startup, but with the job security of an established company
  • ๐Ÿ›ฌ For all international engineers: Promaton is recognized as a visa sponsor by the Dutch government

Job requirements

To apply for this job, we have a couple of hard requirements:

  • 2 years experience in designing, improving and validating deep learning models
  • Familiarity with core deep learning concepts for 2D and 3D image processing
  • Computer science level degree or equivalent degree with a strong mathematical foundation
  • 4 years experience working with Python
  • Experience with software development workflows: Git, GitHub, Testing

Bonus points:

  • Non-deep learning AI-experience: ML, reinforcement learning, constraint satisfaction problems, etc.
  • Experience working with ML on meshes and point clouds
  • Excellent written English skills
  • Experience with uncertainty estimation (Bayesian neural networks)
  • Experience in a regulated environment (complying to ISO norms)
  • Experience with model deployment (AWS, Kubeflow, Tensorflow serving, Docker, etc)
  • Classical digital image processing / computer vision

Sounds like you? Let's talk!