Job Description

About the Role:

We are seeking a Machine Learning Scientist to join our integrated discovery team and help advance small molecule drug discovery programs through applied ML. In this role, leading from the bench, you will enable the development, validation and deployment of state-of-the-art ML models to generate the quantitative predictions necessary to drive drug discovery. Beyond technical mastery, you will serve as a core strategic partner to medicinal chemists, computational chemists, and biologists, building models that move programs efficiently toward program decision points and candidate nomination.

Key Responsibilities:

• Lead the application of Large Language Models (LLMs), co-folding algorithms, and generative chemistry techniques to design novel chemical matter aimed at hitting key program milestones, such as establishing selectivity windows and optimizing drug-like properties
• Serve as the machine learning POC on cross functional projects partnering with medicinal chemists and structural biologists to refine SAR and structure informed modeling efforts
• Synthesize complex ML outputs into clear, actionable design hypotheses that cross-functional scientific stakeholders can use to make high-stakes program decisions
• May be responsible for management and development of internal team members

Required Qualifications:

• Ph.D. in Computational Chemistry, Computer Science, Machine Learning, or a related field
• 2+ years applying ML methods in a small molecule drug discovery programs in biotech or pharma environments
• Demonstrated expertise in statistics, probability theory, data modeling, machine learning algorithms, and the languages used to implement analytics solutions
• Demonstrated success in a cross-functional environment, including biologists, structural biologists, medicinal and computational chemists, with specific examples of computational designs/algorithms/models that directly influence achievement of program milestones
• Strong practical proficiency in Python and deep learning libraries (e.g., PyTorch, TensorFlow) is required. Demonstrated ability to build and maintain robust, production-quality ML code and data workflows

Preferred Qualifications:

• Proven experience with protein-ligand co-folding models (e.g.,Boltz, OpenFold, AlphaFold, etc) and the ability to integrate these structural insights into broader ML discovery pipelines
• Expertise fine-tuning existing models with internally generated structural biology and biology data
• Strong knowledge of deep learning frameworks, specifically for affinity prediction, ADMET modeling, and the application of LLMs in a biological or chemical context
• Experience mentoring and developing teams

Skills & Competencies:

• A demonstrated track record of innovation in the ML/AI space, including developing and validating new architectures or novel applications of existing models to solve complex drug discovery problems
• Demonstrated expertise using small molecule drug discovery ML/AI tools e.g. AlphaFold, Boltz, OpenFold, ChemProp, DeepChem, Reinvent, etc)
• Strong level coding for ML tasks including knowledge of key packages (RDKit, scikit-learn, numpy, pandas, pytorch, DeepChem, polars, PyG/DGL).
• Strong interpersonal and communications skills in the "why" behind a design to a diverse scientific audience