Senior Scientist I, AI/ML for Drug Discovery

Overview

EDDC is Singapore's national drug discovery platform, working with public and industry partners to advance novel therapeutics in oncology, inflammatory and autoimmune diseases.

We are seeking a Data Scientist to join the AI/ML for Drug Discovery group who can run projects end-to-end and works AI-first: using coding agents and agentic workflows as a core part of how analyses, data pipelines and tools get built. We welcome applicants from bioinformatics, data science, or data engineering backgrounds. What matters is biological understanding, systems-level thinking about data, sound judgement, and the ability to keep learning emerging technologies and apply them, while helping shape the group's scientific direction.

Responsibilities

• Own computational projects end-to-end, from problem scoping to delivery, prioritising by impact, aligning stakeholders and communicating results clearly to senior leadership and cross-functional teams.
• Analyse multi-omics data (genomics, bulk, single-cell and spatial transcriptomics, proteomics) to identify and prioritise therapeutic targets, mechanism of action and biomarkers.
• Build and deploy machine learning models, including biological foundation models, to generate and test hypotheses that advance the drug discovery pipeline.
• Use coding agents and agentic workflows to build analyses, pipelines and internal tools faster, and to automate routine data and analysis work.
• Validate AI-generated outputs rigorously, setting standards for testing, reproducibility and scientific correctness.
• Apply systems thinking to understand and optimise the full data lifecycle, from how biological, clinical, and commercial data is generated, structured, and ingested, to how outputs are deployed and used, bridging data infrastructure, analytics, and decision-making.
• Work closely with biologists, chemists, clinicians, and project leads to integrate data into discovery and de-risking frameworks that support project prioritisation, elevation, and pipeline decisions.

Requirements

• PhD in a relevant quantitative or biological field, or equivalent industry experience of the same depth.
• Strong experience working with complex biological and multi-omics datasets, with sufficient biological foundation to engage credibly with scientists.
• Proficiency in Python and R, and working knowledge of data infrastructure including cloud-based systems, APIs, databases, and workflow frameworks.
• Track record of leading projects end-to-end, influencing decisions across technical and non-technical stakeholders.
• Demonstrated hands-on use of coding agents or agentic workflows to deliver real work, in a job or in personal projects.
• Evidence of fast self-directed learning and good judgement in checking AI outputs.
• Hands-on experience with biological foundation models (nucleotide, protein, cell) or ML for biological data is an advantage.
• Experience in pharmaceutical or biotech companies is an advantage.