Data Scientist

About the role

We’re looking for a Data Scientist to develop cutting-edge algorithms that unlock insights from complex, noisy time-series data. You’ll work directly with data from our core nanopore technologies, analysing signals and creating new applicationsusing techniques from deep learning, probabilistic modelling, and dynamic programming. Collaborating closely with our scientists and engineers, you’ll turn experimental data into actionable outputs and scalable tools. This is a unique opportunity to bring state-of-the-art ML techniques into real-world proteomics—and shape the future of biomedical discovery.

Tasks and responsibilities

• Provide expert technical support for analyses of new experiments and applications
• Research, design, and implement algorithms for analysing time-series data from our core technologies
• Collaborate with data scientists and engineers to integrate models into pipelines and tools.
• Document methods and support reproducibility, validation, and publication where appropriate.
• Stay current with academic and industry advances in temporal modelling and deep learning.

Qualifications

• Strong programming and modelling skills in Python with knowledge of machine learning frameworks(e.g. PyTorch, TensorFlow, JAX).
• Broad knowledge of statistical and numerical techniques for data analysis
• In-depth knowledge of machine learning for time-series, including RNNs, LSTMs, GRUs, transformers & other attention mechanisms.
• Solid understanding of probabilistic models (HMMs, Bayesian inference, graphical models).
• Experience designing or adapting dynamic programming algorithms.
• A PhD in numerate discipline, or a Master's degree andrelevant industry experience
• Ability to work in a research-style setting and translate ideas into production- ready code.

Desirable

• Experience working with biological or biomedical time-series data, or other noisy data (e.g., electrophysiology, proteomics, sensor data).
• Familiarity with domain-specific data types (e.g. biological sequence data, microscopy, nanopore sensing).
• Publications or open-source contributions in relevant areas.
• Experience optimising scientific computing code (e.g., JAX, CUDA, Cython).
• Exposure to model interpretability and regulatory considerations in biotech/healthcare.

#J-18808-Ljbffr