Sr. Data Scientist

Metabolon is seeking a Senior Data Scientist with strong modelling expertise to develop advanced statistical and machine‑learning solutions for metabolomics and other omics datasets. This role drives deeper biological insight, predictive analytics, and data‑driven decision‑making across research and product development.

The Senior Data Scientist will design and implement modelling approaches that extract meaningful biological signals from high‑dimensional LC‑MS datasets. The ideal candidate combines strong statistical thinking, machine‑learning expertise, and hands‑on experience with omics data, particularly metabolomics.

This position works closely with bioinformatics, software engineering, and scientific teams to develop robust modelling frameworks and production‑ready analytical tools that support both research and customer‑facing applications.

Position will work remotely, with ideal home location in Ireland or United Kingdom. 

Modelling & Machine Learning

• Develop predictive, statistical and probabilistic models that drive biological insight and support product and research decisions.
• Design and evaluate end‑to‑end machine‑learning workflows, including feature engineering, model training, validation, and performance assessment.
• Apply advanced modelling approaches such as:
  • Probabilistic and Bayesian models
  • Regression and supervised learning methods
  • Latent variable and custom model-based approaches where appropriate
• Construct and adapt statistical and machine learning models from first principles or based on literature where needed.
• Develop models relevant to metabolomics applications such as retention time prediction, compound identification and peak assignment.

Data Processing & Feature Engineering

• Develop methods to transform raw LC‑MS metabolomics data into modelling‑ready datasets.
• Implement feature‑selection, normalization, batch‑correction, and noise‑reduction approaches.
• Ensure reproducible, well‑documented, and scalable data‑processing pipelines.

Computational Method Development

• Design and evaluate new computational approaches for analyzing metabolomics data.
• Benchmark modelling methods across diverse datasets.
• Collaborate with bioinformatics and software teams to integrate models into analytical pipelines and applications.

Collaboration & Communication

• Work with scientists, engineers, and product teams to translate modelling insights into usable tools.
• Present modelling results and interpretations to both technical and non‑technical stakeholders.
• Contribute to best practices in reproducible science and ML development.

• Master’s degree in Bioinformatics, Computational Biology, Computer Science, Statistics, Applied Mathematics, or a related field. D. preferred.
• 7+ years experience in with ML workflows from feature extraction through deployment.Strong computational background with proficiency in efficient, production‑quality code (ideally Python).
• Experience with code version control (e.g. git) and code‑testing practices.
• Experience developing models for metabolomics data analysis, especially for compound identification, feature annotation or retention time prediction preferred.
• Experience with probabilistic programming or Bayesian modelling tools such as PyMC, Stan, NumPyro, or similar frameworks a strong plus.
• Experience working in cloud environments (e.g. AWS) and with containerization (e.g. Docker) preferred.
• Solid understanding of core machine‑learning methods, statistical inference, and probabilistic modelling.
• Familiarity with inference methods such as MCMC, variational inference, expectation maximization, or related approaches preferred.
• Strong knowledge of metabolomics or other omics.
• Knowledge of ML engineering practices, including pipelines, deployment, and MLOps preferred.
• Excellent communication and collaboration skills.

Metabolon, Inc., is the global leader in revealing biological insights on disease state and physiological reactions in the present time through metabolomics. Leveraging one of the world’s most diverse and rich patient data sets, Metabolon is equipped to deliver biologically relevant evidence to address some of the most difficult and pressing questions in the life sciences. Every day, our work is helping to accelerate research and product development success in the biopharma, population health, consumer products, agriculture, wellness, and academic research sectors.

Metabolon was founded in 2000 and is headquartered in Research Triangle Park, North Carolina. For more information, please visit www.metabolon.com.

Metabolon is an Equal Opportunity Employer and does not discriminate against any employee or applicant for employment because of race, color, religion, gender, sexual orientation, gender identity, national origin, age, disability, veteran status, or any other protected status prohibited under Federal, State, or local laws. All employment decisions are based on valid job‐related requirements.