Microsoft Researcher BioEmu Machine Learning & Molecular Biology 

Taiwan, Taoyuan City 

531313828

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.

You’ll work on problems that don’t yet have well‑defined benchmarks. Where part of the innovation is deciding what to optimise and proving it matters for biology. It’s an opportunity to bridge state‑of‑the‑art ML with meaningful biomedical impact in a

Required/Minimum Qualifications:

• Masters or PhD or equivalent experience in Machine Learning, Physics, Chemistry, or a related discipline.
• Experience developing computational methods or machine learning models.
• Strong communication skills to work effectively in an interdisciplinary team, including explaining technical concepts to collaborators from diverse backgrounds.

Other Requirements:

Candidates should have deep expertise in some discipline relevant to the project, for example:

• Deep learning methods in structural biology
• Designing and producing large scale datasets for machine learning
• Collaborative code development in a shared codebase
• Large-scale, distributed model training and other workflows
• Computational methods to make use of real-world biological data (cryo-EM, binding affinity assays, etc.)
• Computational biology / bioinformatics workflows
• Molecular dynamics simulation, rare event sampling and statistical mechanics

Preferred/Additional Qualifications:

• Capability to align research goals with external collaborators and apply computational data generation efforts and model development to real-world health challenges such as drug design

• Create novel ML techniques and the datasets needed to train them for biomolecular structure, dynamics, and function.
• Design, implement, and iterate on model architectures and training algorithms (e.g., diffusion/sequence–structure models, representation learning).
• Define success where standards don’t exist: propose sound benchmarks and metrics to evaluate model quality and real‑world utility.
• Build high‑quality research code (Python/PyTorch) with reproducible workflows and robust data pipelines.
• Partner across disciplines —communicate clearly with ML researchers and experimental/computational biologists; present results and influence direction.
• Work autonomously and as a team player, regularly reporting insights, risks, and next steps.
• Thrive on imperfect, heterogeneous data, applying rigorous data curation, augmentation, and uncertainty‑aware evaluation to “messy” real‑world datasets.
• Aim for impact: translate promising ideas into artifacts others can use (papers, code, models, datasets).