Microsoft Principal Applied Researcher - AI Science 

Taiwan, Taoyuan City 

783648158

At , we believe machine learning and artificial intelligence has the potential to transform scientific modelling and discovery crucial for solving the most pressing problems facing society including sustainable materials and discovery of new drugs.

Required:

• PhD or equivalent research experience in Chemistry, Biophysics, Physics, Computer Science, Bioinformatics or a related field.
• Track record of impactful research on biomolecular structure/dynamics or ML for biology (e.g., strong publications, open‑source, or shipped analyses).
• Excellent technical communication for interdisciplinary work.
• Comfortable with real‑world data that lack structure/cleanliness/completeness.
• Fluency building scalable Python pipelines; experience running large studies or analyses on cloud/HPC.

Preferred:

• Industry experience in pharma/biotech or industrial research.
• Experience guiding large‑scale experimental data generation (e.g., cryo‑EM campaigns, screening, binding/functional assays), including QC/QA, metadata, and data governance.
• Familiarity with model‑guided experimental design (active learning) and uncertainty quantification.
• Experience with distributed ML training/inference and cost/performance trade‑offs on HPC or cloud systems.

• Scientific leadership without silos: lead an effort to apply BioEmu at scale to generate biological insights and hypothesis for drug discovery. Be the principal contact point for world-leading collaborators and drug hunters. Contribute to and closely align with project leadership to strive for maximum impact. Prioritize team success over personal agenda.
• Model biomolecular structure and dynamics at scale: Use BioEmu, structure/sequence databases, and complementary tools to analyze proteins and complexes.
• Collaboration with drug designers & external partners: Lead day‑to‑day technical collaboration with pharma/biotech partners and CROs; define joint objectives, success metrics, and Go/No‑Go criteria; ensure traceability and reproducibility of decisions.
• Support and oversee data generation at scale: Design prospective studies with wet‑lab teams (e.g., binding/kinetics assays, structural campaigns such as cryo‑EM or crystallography); plan sample selection via active learning/uncertainty; manage data quality, metadata standards, and data rights.
• Generate biological hypotheses and insights: Integrate biomolecular structure and dynamics data to generate experimentally-testable predictions and biological insights.
• Systems & tooling at scale: Guide robust pipelines for large‑scale inference/analysis on Azure; ensure cost‑aware compute/storage use; codify best practices in code and documentation.
• Stakeholder communication: Author clear technical narratives for collaborators and internal leadership; present results credibly to mixed audiences; preempt risk with measurable mitigation plans.
• Mentor & uplift: Manage and coach applied researchers and engineers.