Postdoctoral Machine Learning Engineer/Data Analyst, BTI

We are seeking a Machine Learning Scientist/Engineer to develop and deploy data-driven models that improve biomanufacturing processes for recombinant proteins, mRNA, cell and gene therapies. The role focuses on applying ML to upstream and downstream process data, analytical datasets, and manufacturing systems to enhance yield, quality, robustness, and process understanding of therapeutics. 

Key Responsibilities

Machine learning and data analytics

• Develop ML models for process optimisation, prediction, and control, including yield, CQAs, aggregation, glycosylation, and impurity profiles.
• Apply supervised, unsupervised, and multivariate methods (e.g. neural networks, regression, classification, clustering, PCA/PLS, Bayesian models).
• Integrate omics, analytical (LC-MS, spectroscopy), and process data into unified modelling frameworks.
• Perform feature engineering informed by bioprocess and product knowledge.

Biomanufacturing applications

• Digitially Improve AI driven upstream processes (e.g. CHO cell culture, fermentation, feeding strategies).
• Digitially Improve AI driven downstream processes (e.g. chromatography, filtration, formulation, aggregation control).
• Develop soft sensors and digital twins for real-time or near-real-time process monitoring.
• Replace or augment design of experiments (DOE) with ML-driven process optimisation.

Deployment and validation

• Translate models into production-ready tools (Python/R, APIs, dashboards).
• Perform model validation, versioning, and lifecycle management.

Collaborative environment 

• Work closely with process scientists, analytical scientists, engineers, and quality teams.
• Clearly communicate model assumptions, limitations, and impact to non-ML stakeholders.

Required qualifications

• PhD in Machine Learning, Data Science, Chemical/Biochemical Engineering, Bioinformatics, Systems Biology, or related field.
• Strong programming skills in Python (e.g. scikit-learn, PyTorch, TensorFlow).
• Experience with structured, sparse, and noisy experimental datasets.
• Solid understanding of statistics, experimental design, and model validation.

Desirable experience

• Experience in biomanufacturing, bioprocessing, or pharmaceutical development.
• Experience with LC-MS, spectroscopy (Raman, NIR), PAT, or omics data.
• Knowledge of process control, digital twins, or mechanistic-ML hybrid models.
• Experience working with cloud platforms, MLOps, or data pipelines.

Key competencies

• Modelling mindset
• Strong problem-solving and analytical skills
• Ability to work with incomplete or heterogeneous datasets
• Excellent communication 

What we offer:

• Opportunity to apply ML to real-world, high-impact manufacturing challenges
• Collaborative environment at the interface of AI, biology, and engineering
• Exposure to cutting-edge therapeutics and advanced manufacturing platforms

The above eligibility criteria are not exhaustive. A*STAR may include additional selection criteria based on its prevailing recruitment policies. These policies may be amended from time to time without notice. We regret that only shortlisted candidates will be notified.