Role overview
In the short to medium term, this role will primarily focus on advancing the development and optimisation of state-of-the-art language decoding models. The successful candidate will play a key role in designing, training, and evaluating models that leverage both classical fMRI datasets acquired by Karavela, as well as external datasets, and progressively incorporate raw k-space data as it becomes available through Karavela’s data collection efforts.
This position offers a unique opportunity to work at the intersection of neuroscience, machine learning, and data engineering, contributing to cutting-edge research with real-world clinical and technological applications.
What we're looking for
Preprocessed (classical) fMRI datasets generated internally and sourced externally;
Raw k-space data, supporting the transition toward end-to-end modelling approaches as new data becomes available.
Design, implement, and optimise machine learning algorithms and pipelines, ensuring scalability, reproducibility, and high performance.
Produce high-quality individual contributions, including but not limited to:
Well-documented, production-ready code;
Peer-reviewed research publications and technical reports;
Internal documentation and knowledge-sharing materials;
Active participation in scientific conferences, workshops, and industry events.
Collaborate closely with cross-functional teams, including:
The modelling team, to align on architectures, methodologies, and evaluation strategies;
Data collection teams, to understand data generation processes and ensure optimal data usability;
Clinical and application teams, to translate research outputs into practical, real-world solutions.
Contribute to the overall scientific direction and strategic roadmap of the project by:
Identifying new research opportunities and proposing innovative approaches;
Staying up to date with the latest developments in relevant fields;
Supporting decision-making through technical insights and evidence-based recommendations.
Ensure adherence to best practices in research integrity, data governance, and ethical AI development.
Experience working with neuroimaging data (e.g., fMRI) and/or signal processing (experience with k-space data is a plus);
Proficiency in programming languages such as Python and familiarity with ML frameworks (e.g., PyTorch, TensorFlow);
Proven track record of research contributions (publications, projects, or equivalent);
Strong communication and collaboration skills, with the ability to work effectively in multidisciplinary teams.