(Senior) Machine Learning Scientist
Abiologics · Watertown, MA
About this role
## (Senior) Machine Learning Scientist **Abiologics, Inc.** ### About the Role Train, validate and ship predictive models powering our molecular design platform. Build models that score chemical molecules for developability (ADMET), potency, synthesizability and 3D structure, working alongside chemists, biologists and platform engineers. **First-year success:** 2-3 models in production with documented benchmarks, calibrated uncertainty, and clear applicability domain. ### What You'll Do - Train and maintain ML models for ADMET and developability endpoints (solubility, permeability, metabolic stability, toxicity, aggregation risk) - Build potency and binding models (QSAR, ligand- and structure-based) to rank molecules - Develop synthesizability models: synthetic accessibility scoring, reaction-outcome prediction, retrosynthesis-informed filters - Apply and fine-tune structure-aware models (GNNs, equivariant networks, protein-ligand structure) - Curate assay data, define benchmarks, quantify uncertainty and applicability domain - Package models for production with engineers: versioned, reproducible, monitored for drift - Present results and model limits to chemists; incorporate feedback into retraining ### What You Bring - PhD in computational chemistry, cheminformatics, ML or related field (or MS + 3-6 years industry experience) - Demonstrated experience training/validating ML models on chemical/molecular data with shipped or published results - Direct experience with ≥2 of: ADMET/developability, potency/binding, synthesizability/retrosynthesis, protein/ligand structure - Fluency with molecular representations (fingerprints, descriptors, graphs, 3D) and RDKit - Strong Python and deep learning framework (PyTorch preferred); GNN or transformer experience on molecules - Rigorous evaluation: scaffold/temporal splits, baselines, noisy-label handling, uncertainty estimation - Clear communication with chemists and biologists ### Nice to Have - Publications, open-source contributions or competition results in molecular ML - Generative design, active learning or Bayesian optimization experience - Large-scale training, MLOps and model serving - Docking, free-energy methods or protein structure prediction tools - Biologics or non-small-molecule modality experience ### Compensation **Salary Range:** $132,000 - $258,500 (based on qualifications, skills, competencies, experience) Healthcare coverage, annual incentive program, retirement benefits and broad range of other benefits. --- *Flagship Pioneering is committed to equal employment opportunity and building diverse, inclusive teams. We encourage applications from candidates with transferable skills and passion, even if you don't meet every requirement.*
Listing freshness
CronJobs last confirmed this listing 47m ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.