Sr./ Machine Learning Scientist

Location: Great Boston/New York

We’re looking for an ML Scientist to help drive and evolve our machine learning platform across predictive modeling, generative design, uncertainty quantification, and optimization. You’ll work with deep learning–based approaches for molecular representation and property prediction, helping connect model outputs directly to experimental decisions.

This role sits at the intersection of cutting-edge ML research and real-world drug discovery, where your work will directly influence which compounds are prioritized and advanced.

Job Responsibilities:

• Develop and refine machine learning models for molecular property prediction
• Apply deep learning approaches (including graph-based methods) to chemical data
• Collaborate closely with chemistry and computational teams to translate model outputs into actionable insights
• Contribute to workflows that support compound design, optimization, and prioritization
• Evaluate and implement emerging ML techniques within a production setting
• Help build and maintain scalable modeling infrastructure

Qualifications:

Required

• PhD in machine learning, computational chemistry, cheminformatics, or a related field (or MS with relevant industry experience)
• 0–5 years of experience applying deep learning methods (e.g., graph neural networks) to molecular or chemical data
• Strong programming skills in Python, with experience in frameworks such as PyTorch and GNN libraries (PyG, DGL, or similar)
• Solid understanding of drug discovery fundamentals (e.g., ADME, SAR, molecular properties)
• Experience with uncertainty quantification approaches (e.g., Bayesian methods, ensembles, or related techniques)
• Proven ability to translate research into practical, production-ready code
• Ability to travel to New York 1-2 a month

Preferred

• Experience with optimization techniques such as active learning, Bayesian optimization, or multi-objective optimization
• Familiarity with cheminformatics tools (e.g., RDKit, Open Babel)
• Publications in machine learning or computational biology-related venues
• Experience with generative modeling approaches for molecular design (e.g., VAEs, diffusion models)
• Exposure to cloud environments (AWS, GCP) and scalable ML workflows
• Comfortable working in a fast-paced, startup environment with end-to-end ownership

Why this company?

• Closed-loop validation: Your models are tested in the real world through rapid cycles — no “publish and pray.” You’ll see how your predictions perform and iterate quickly
• Meaningful scale: Work across a large, enumerated compound space supported by proprietary chemistry, not just generic virtual libraries
• High autonomy: Join a small AI team reporting directly to the VP of AI, with real input into architectural and strategic decisions
• End-to-end impact: From model architecture to which compounds are synthesized next, your work has a direct line to the lab bench
• Competitive compensation: Salary equity at a well-funded Series A company with strong scientific leadership