Software Engineer - Machine Learning
DescriptionKheiron is a fast-growing, medical technology company using advanced machine learning to develop and deliver intelligent tools for radiologists, radiology departments, imaging centers and hospitals to improve the efficiency, consistency and accuracy of radiology reporting. Our aim is to save lives by empowering radiologists to faster diagnosis and treatment, resulting in better patient outcomes.As a core member of the Machine Learning team at Kheiron, you will be responsible for building an infrastructure that facilitates state of the art deep learning research. This includes large scale medical data processing, efficiently scaling machine learning models to large compute clusters, and tooling to help visualise patterns in the data. You will work closely with our Product, Data, and Systems teams to bring solutions to real and important problems into the clinic and every part of the business.
- Basic Machine Learning and Computer Vision understanding.
- Strong software engineering skills (knowledge of professional software engineering best practices for the full software development life cycle, strong OO design skills).
- Ability to write well-structured and tested code in Python or another relevant programming language (e.g. Java, Go, C++).
- Python, C++ or Cuda experience.
- Implement and scale cutting-edge machine learning algorithms.
- Work with a variety of stakeholders, including data, research and product engineers.
- Report and present software developments including status and results clearly and efficiently both internally and externally, verbally and in writing.
- Design, implement and deliver complex pieces of infrastructure, tooling and research as part of a multi-disciplined engineering team.
- The opportunity to work alongside a dedicated team, at the cutting edge of research, creating products to help in early prevention of cancer
- Competitive salary, dependent on experience
- % Equity (share options) in the company
- The opportunity to travel to conferences
- Cycle2Work Scheme