Director, ADMET & PK/PD Modeling

• Set the technical direction for federated learning and molecular AI across TuneLab
• Define a research agenda unifying privacy-preserving foundation models, multi-task learning, and generative small-molecule design
• Align research strategy with platform and portfolio priorities
• Serve as a principal technical authority and mentor for data scientists and engineers
• Guide experimental design, review methods and code, and influence technical decisions across disciplines and external partnerships
• Architect Transformer- and graph-neural-network-based architectures for federated pre-training
• Advance semi-supervised and self-supervised learning methods for federated learning
• Develop communication-efficient federated aggregation strategies including FedAvg, FedProx, and SCAFFOLD
• Profile and optimize memory, latency, and communication costs of federated training and inference
• Build simulation environments to test, debug, and benchmark federated strategies
• Architect federated multi-task learning models and address task and feature heterogeneity
• Create fine-tuning and downstream adaptation protocols and rigorous validation frameworks
• Build multi-task small-molecule property models covering ADMET, solubility, permeability, metabolic stability, and off-target liabilities
• Design and deploy generative chemistry models for de novo design, lead optimization, and scaffold hopping
• Develop ADMET-driven multi-objective prediction-generation pipelines
• Explore synthetically accessible chemical space through reaction-aware generation, retrosynthetic planning, and fragment-based design
• Learn structure-activity relationships from sparse federated bioactivity data
• Apply explainability techniques to molecular and multi-task models
• Establish benchmarks using public and proprietary data
• Author high-impact publications and deliver internal and external presentations
• Maintain reproducible code, internal libraries, and version control for data, code, and models
• Lead through technical vision, methodological rigor, and mentorship rather than formal people management

Requirements

• PhD in Computer Science, Computational Chemistry, Cheminformatics, Machine Learning, Computational Biology, or a related computational field from an accredited college or university
• 5+ years of post-PhD experience applying machine learning to drug discovery within the biopharmaceutical industry or comparable settings, or an equivalent record of technical leadership and impact; preference for 8+ years
• Demonstrated technical leadership, research direction, complex ML program leadership, and scientist mentorship
• Experience developing generative models for molecular design and multi-task or representation-learning models for complex endpoints
• Deep understanding of medicinal chemistry principles and ADMET optimization
• Hands-on experience with federated learning, distributed optimization, and privacy-preserving machine learning
• Publications in top-tier venues such as NeurIPS, ICML, or ICLR
• Expertise in graph neural networks and geometric deep learning for molecules
• Strong background in organic chemistry and synthetic-feasibility assessment
• Experience with fragment-based and structure-based drug design
• Knowledge of PK/PD modeling and clinical translation
• Proficiency in RDKit, DeepChem, and modern ML frameworks such as PyTorch
• Experience with active learning and design–make–test–analyze cycles
• Familiarity with uncertainty quantification and explainability (XAI) in federated or multi-task settings
• Exceptional communication skills across disciplines and with external partners
• Learning agility and a portfolio mindset
• Independent, self-directed approach to ambiguous research problems

Core Competencies

Demonstrates expertise in federated learning, molecular AI, and generative modeling, with a strong foundation in medicinal chemistry and ADMET optimization. Proven ability to lead complex machine learning programs and mentor scientists while aligning research strategies with organizational priorities.

Highest-signal resume keywords

• PhD In Computer Science
• Federated Learning
• Generative Models For Molecular Design
• Graph Neural Networks
• ADMET Optimization

Hard Skills

• Machine Learning
• Multi-Task Learning
• Experimental Design
• Data Optimization
• Simulation Environment Development
• Fine-Tuning Protocols
• Molecular Property Modeling
• Explainability Techniques
• Active Learning
• PK/PD Modeling

Soft Skills

• Exceptional Communication Skills
• Mentorship
• Learning Agility
• Independent Research Approach

Industry Keywords

• Biopharmaceutical Industry
• Drug Discovery
• Medicinal Chemistry
• Synthetic Feasibility Assessment
• Privacy-Preserving Machine Learning

Tools & Technologies

• RDKit
• DeepChem
• PyTorch
• Version Control Systems
• Publications In NeurIPS
• Publications In ICML
• Publications In ICLR