Senior ML Researcher – Molecular Privacy(m/w/x)

Description

You will lead technical privacy risk assessments for federated drug discovery models, turning complex experimental data into clear, defensible evidence for high-stakes life sciences collaborations.

Requirements

• •Experience with drug discovery ML models
• •Proficiency in structure-based protein-ligand modelling
• •Practical reasoning about privacy risk
• •Experience building structure-based modelling and co-folding
• •Experience with ML privacy or federated learning
• •Ability to design empirical privacy experiments
• •Clear communication of complex technical risks
• •Ownership of ambiguous cross-cutting problems
• •Published technical work in ML or biology
• •Experience in multi-organization industry collaborations
• •Experience defining privacy or risk positions
• •Experience acting as a technical authority

Tasks

• •Design and execute practical privacy risk experiments
• •Map theoretical threats to realistic attack surfaces
• •Analyze molecular and structural machine learning pipelines
• •Identify sensitive signal exposure in modeling choices
• •Build experimental tooling for privacy analysis
• •Conduct generative reconstruction and distributional leakage tests
• •Generate technically credible privacy evidence through modeling
• •Create informative reports for consortium decision-makers
• •Translate empirical findings into clear privacy narratives
• •Collaborate on grounded privacy mitigation strategies
• •Reproduce modeling pipelines for baseline attack assessments
• •Analyze active federated drug discovery programs
• •Run privacy experiments on live federated workflows
• •Synthesize quantitative evidence into stakeholder presentations
• •Act as a technical authority on privacy
• •Evaluate privacy risks under real operational conditions
• •Shape organizational standards for privacy experimentation

Tools & Technologies

Benefits