Artificial Intelligence Specialist

Job Title: Senior Machine Learning / Artificial Intelligence Engineer

Job Type: Full-Time

An innovative, R&D-driven diagnostics organisation is seeking a Senior Machine Learning / Artificial Intelligence Engineer to join a highly skilled research and development team. In this role, you will design and develop novel AI/ML models from scratch, translating complex measured signals from simulations, benchmark testing, and clinical or pilot studies into meaningful, clinically relevant outcomes.

This position focuses on statistical learning, probabilistic and mathematical modelling, and data-driven inference, treating measured signals as abstract inputs. You will be responsible for defining the overall modelling strategy, learning framework, validation methodology, and performance metrics in a context where no prior AI solution exists. A background in applied mathematics, physics, or telecommunications engineering is advantageous but not mandatory.

• Design and implement end-to-end machine learning and AI pipelines that map measured signals to clinically relevant outcomes.
• Develop novel modelling approaches in a greenfield environment with no existing reference solutions.
• Apply and evaluate probabilistic methods (e.g. Markov models, Bayesian inference) and/or deep learning architectures as appropriate.
• Define training, validation, and performance assessment protocols, including uncertainty estimation and robustness analysis.
• Collaborate closely with signal processing engineers, biomedical experts, and clinicians to ensure alignment between AI outputs and clinical interpretation.
• Document algorithms, assumptions, and validation results to support regulatory and clinical discussions.

• Strong expertise in machine learning, artificial intelligence, and/or statistical modelling applied to real-world experimental or clinical data.
• Proven experience building AI models from scratch in environments with limited prior art or labelled data.
• Experience working with time-series or sequential data.
• Solid understanding of probabilistic models such as Markov chains, Hidden Markov Models, Bayesian networks, or related frameworks.
• Proficiency in Python and common ML/AI libraries (e.g. PyTorch, TensorFlow, scikit-learn).
• Ability to translate abstract model outputs into interpretable, clinically meaningful metrics.

• PhD in Machine Learning, Artificial Intelligence, Applied Mathematics, Statistics, Physics, Biomedical Engineering, or a related field.
• Experience working with clinical, biomedical, or pilot-study datasets.
• Background in decision processes, state-space models, or probabilistic inference.
• Familiarity with regulatory or validation constraints in medical or other safety-critical systems.
• Experience working in early-stage or exploratory R&D environments.