Machine Learning Scientist, Cryo-EM Cell Mapping

Rosalind Franklin Institute; East Hagbourne; Hybrid; GBP 35.000 - 42.000; Vollzeit

Benefits dieser Stelle

25 days holidays

Generous pension scheme

Group Life Assurance

Buying and Selling Annual Leave

Hybrid and flexible working

Training and development opportunities

Bus pass discount scheme

Cycle to Work Scheme

Perkbox employee platform access

Occupational Health support

Zusammenfassung

The Rosalind Franklin Institute invites applications for a Research Associate to advance molecular mapping in cryo-electron tomograms. The role will develop machine-learning methods for particle localisation, detection and classification in crowded cellular volumes, with emphasis on learning from limited annotations and generalisation to new datasets and molecular species.

Working with experimental and computational colleagues, you will build robust benchmarks, create reproducible software, and

Qualifikationen

• PhD/DPhil (or equivalent) required; candidates with submitted thesis considered.
• Experience applying machine learning to image data and subtomogram analysis.
• Strong publication record and ability to work in interdisciplinary teams.

Aufgaben

• Develop and apply machine-learning methods to broaden detection in cryo-electron tomograms.
• Collaborate with experimental and computational colleagues to prepare datasets and validate findings.
• Develop reproducible analysis workflows and software, and share results via documentation and publications.
• Plan data acquisitions with experimentalists and deliver outputs such as reports or presentations.
• Contribute to outputs from research including papers and presentations; supervise students or visitors.

Kenntnisse

Machine learning

Data analysis

Scientific writing

Team collaboration

Ausbildung

PhD or equivalent

Tools

Python

Machine Learning Frameworks

Jobbeschreibung

The Rosalind Franklin Institute invites applications for a Research Associate to advance molecular mapping in cryo-electron tomograms. The role will develop machine-learning methods for particle localisation, detection and classification in crowded cellular volumes, with emphasis on learning from limited annotations and generalisation to new datasets and molecular species.

Working with experimental and computational colleagues, you will build robust benchmarks, create reproducible software, and