(Senior) Machine Learning Scientist

Flagship Pioneering•Watertown, MA

About The Position

Abiologics, Inc., an early-stage biotechnology company founded in Flagship Pioneering’s venture creation engine, is developing Synteins, a class of macromolecular medicines enabled by synthetic and computational technologies. The company is hiring a Machine Learning Scientist to train, validate, and deploy predictive models for its molecular design platform. The models will score molecules for developability, potency, synthesizability, and 3D structure, in collaboration with chemists, biologists, and platform engineers. In the first year, success means having two or three models in production use by project teams, with documented benchmarks, calibrated uncertainty, and a clearly defined applicability domain. The role includes communicating model results and limitations to project teams and incorporating their feedback into retraining.

Requirements

PhD in computational chemistry, cheminformatics, machine learning, or a related field, or an MS plus equivalent industry experience (about 3–6 years of hands-on modeling).
Demonstrated experience training and validating machine-learning models on chemical or molecular data in industry or academia, with shipped or published results.
Direct experience in at least two of the following areas: ADMET/developability, potency/binding, synthesizability/retrosynthesis, or protein or ligand structure.
Fluency with molecular representations such as fingerprints, descriptors, graphs, and 3D representations, and tools such as RDKit.
Strong Python skills and experience with a deep-learning framework; PyTorch is preferred.
Experience with GNNs or transformers applied to molecules.
Rigorous evaluation practices, including scaffold or temporal splits, baselines, noisy-label handling, and uncertainty estimation.
Clear communication with chemists and biologists.

Nice To Haves

Publications, open-source contributions, or competition results in molecular machine learning.
Experience with generative design, active learning, or Bayesian optimization loops.
Experience with large-scale training, MLOps, and model serving.
Familiarity with docking, free-energy methods, or protein-structure prediction tools.
Experience working with biologics or non-small-molecule modalities.

Responsibilities

Train and maintain machine-learning models for ADMET and developability endpoints, including solubility, permeability, metabolic stability, toxicity, and aggregation risk.
Build potency and binding models, including QSAR, ligand-based, and structure-based approaches, to rank and prioritize molecules against targets.
Develop synthesizability models, including synthetic-accessibility scoring, reaction-outcome prediction, and retrosynthesis-informed filters.
Apply and fine-tune structure-aware models, such as GNNs, equivariant networks, protein-ligand structure models, and docking-informed machine learning.
Curate and clean assay data; define scaffold- or time-split benchmarks; and quantify uncertainty and applicability domain.
Package models for the platform in collaboration with engineers, ensuring they are versioned, reproducible, and monitored for drift.
Present model results and limitations to chemists and project teams, and incorporate their feedback into retraining.