Research Associate in Machine Learning for Astronomical Imaging (Fixed Term)

University of Cambridge; Cambridge; On-site; GBP 37,000 - 46,000; Full time

Job summary

The University of Cambridge seeks two Research Associates to join an ambitious research programme in machine learning for astronomical imaging, led by Dr. Miles Cranmer (DAMTP/IoA) and Professor Vasily Belokurov (IoA).

The role focuses on developing novel AI methods for detecting and characterising low surface brightness features in wide-field imaging and scaling these methods to forthcoming surveys. You will design and build the software stack for large survey data, spanning pipelines, training

Qualifications

• PhD or near completion in machine learning, computer science, astronomy, physics, mathematics, or related computational discipline.
• Strong ability to communicate technical material to diverse audiences.
• Willingness to supervise student projects and deliver seminars.

Responsibilities

• Conduct original research on ML approaches to source detection, deblending and low surface brightness feature recovery.
• Develop and maintain software stack for large survey datasets, including data pipelines, training/inference infrastructure, and HPC deployment.
• Publish results in peer-reviewed journals and present at international conferences; release open-source software.

Education

PhD or close to completion (thesis submitted)

Job description

The University of Cambridge seeks two Research Associates to join an ambitious research programme in machine learning for astronomical imaging, led by Dr. Miles Cranmer (DAMTP/IoA) and Professor Vasily Belokurov (IoA). The primary function of these posts is research and innovation: developing novel AI methods for the detection and characterisation of low surface brightness structure in wide-field astronomical imaging and advancing these methods to operate at the scale of forthcoming surveys.

The role holders will conduct original research into machine learning approaches to source detection, deblending, and low surface brightness feature recovery, including generative and simulation-based methods. Alongside this research, they will design and build the software stack that applies these methods to large survey datasets, spanning data pipelines, model training and evaluation infrastructure, and deployment on GPU and HPC systems. They will publish their results in peer-reviewed journals, present at international conferences, and release open-source research software associated with the programme.

The posts are funded by a philanthropic gift. The role holders will work closely with the research groups of Dr. Cranmer and Professor Belokurov and will have access to new wide-field imaging data through the programme's links to observational surveys.

Duties include developing and conducting individual and collaborative research objectives, proposals and projects. The role holders will be expected to plan and manage their own research and administration, with guidance if required, and to assist in the preparation of proposals and applications to external bodies. You must be able to communicate material of a technical nature and be able to build internal and external contacts. You may be asked to assist in the supervision of student projects, the development of student research skills, provide instruction, or plan/deliver seminars relating to the research area.

The successful candidate will have a PhD, or close to completion of a PhD (thesis submitted), or equivalent research experience to a PhD, in machine learning, computer science, astronomy, physics, mathematics, or a related computational discipline.

Fixed-term: The funds for this post are available for 3 years in the first instance.

Informal inquiries can be made by contacting Dr Miles Cranmer at [e-mail].

If you have any queries about the application process, please email [e-mail].

The closing date for applications is Monday, 21 September 2026.

Interviews will be held shortly after the closing date.

The University actively supports equality, diversity and inclusion and encourages applications from all sections of society.

The University has a responsibility to ensure that all employees are eligible to live and work in the UK.