Sonja Adomeit // Machine Learning Engineer

Room to grow: How flexibility and trust encouraged my growth as a machine learning engineer


Our first employee testimonial is from Sonja Adomeit, a former machine learning engineer in our Research & Development team.

After ending her time at RAYLYTIC in August 2022, she has gone on to pursue a PhD in Models for Personalized Medicine at the University of Heidelberg

Read more below about Sonja’s work on an algorithm for the automatic analysis of X-ray images as part of completing her master’s thesis at RAYLYTIC and her continued employment as a machine learning engineer. 

Sonja Adomeit | Machine Learning Engineer

One of RAYLYTIC’s three core values is “The Team,” or the employees that make up the backbone of our company. That’s why we provide our current employees as well as alumni a platform to share their experiences at RAYLYTIC in the form of testimonials. These are meant to give insight into our corporate culture and highlight how our employees evolve and develop as professionals during their time here. 

We are proud to share the individual and collective efforts that have a long-lasting impact on the trajectory of our employees, paving the way for their future success.

What was your position at RAYLYTIC?

I began at RAYLYTIC by writing my master’s thesis in the R&D Team and was then hired as a machine learning engineer. My main task was to develop an algorithm that could use spinal X-ray images to determine essential coronal parameters – like shoulder balance or Cobb angles in patients with scoliosis. 

The accurate measurement of these kinds of parameters is critical for surgical planning and conducting before-and-after comparisons. Teamwork was a huge part of this project: I was not only in close cooperation with my department, but also with two doctors. 

After developing the algorithm, we were able to test it by comparing it to measurements conducted by experts. The correlation was so convincing  that we were able to successfully submit abstracts to different events where we will be presenting the results this year. 

What did you do before RAYLYTIC?

I received my M.S. degree in Business Information Studies at the Konstanz University of Applied Sciences in in Konstanz, Germany. During my degree and before my time at RAYLYTIC, I had different business-related student jobs. 

Example workflow of the algorithm developed by Sonja and the RAYLYTIC R&D Team for the automatic computation of essential measurements in the treatment and diagnosis of scoliosis. 

What did you appreciate most about your time at RAYLYTIC as a machine learning engineer?

Working scientifically and the flexibility of the company: I played a part in scientific studies and could work from home along the way. 

What was the application process like?

I first got tasked with a coding challenge that I had a week to complete. Here, I had to demonstrate basic knowledge in software engineering and machine learning. Afterwards, I had an interview with HR and a second interview with the department. 

Reasons why you're changing jobs?

I was offered the opportunity to pursue a PhD at the University of Heidelberg and to go deeper into academic and scientific work. 

Why do you think applicants should choose RAYLYTIC for working as a machine learning engineer?

RAYLYTIC is a technology company in the healthcare industry, so they are at the forefront of digitalizing and automating the healthcare sector, which ultimately helps patients on their way to recovery. 

The team is also very young and diverse, which I really enjoyed during my time here. A huge plus was the fact that I could work 100% remotely and didn’t have to relocate. This made applying to a company in a different city a lot easier. 

The option for remote work also made working during the COVID-19 pandemic much safer. The fact that RAYLYTIC offers completely remote work showed me how large their appreciation of and trust in their employees is. 

Arrange a free and non-binding demo appointment

UNITY Research: Powerful analysis and controlling tools to conduct clinical studies efficiently.