(Senior) Scientist, Machine Learning

Flagship Pioneering, Inc.•Cambridge, MA

9h•$132,000 - $258,500•Onsite

About The Position

Expedition Medicines is a privately held, early-stage biotechnology company pioneering the emerging field of Protein Editing. At Expedition Medicines we create small molecules that edit protein structure and function to unlock presently undruggable targets and a broad array of therapeutic modalities. Our platform integrates novel small molecule chemistry and chemoproteomic discovery technologies with Machine Learning (ML) to enable generative design. Expedition Medicines is backed by Flagship Pioneering, bringing their courage, vision, and resources to guide Expedition Medicines from platform validation to patient impact. We are seeking collaborative, relentless problem solvers that share our passion for impact to join us! Expedition is seeking a motivated and innovative (Senior) Scientist, Machine Learning to join our team. In this role, you will play a critical role in developing, evaluating, and applying machine learning approaches that connect Expedition’s proprietary chemoproteomics data with quantum chemistry, electronic structure, and generative molecular design. The successful candidate will combine strong expertise in modern machine learning with a deep understanding of molecular representation, quantum chemistry, and computational drug discovery to drive impact across Expedition’s drug discovery programs. This individual will contribute to the advancement of a state-of-the-art AI platform for covalent drug discovery, with a focus on linking large-scale atom-precision experimental data to physically meaningful features such as electronic structure, reactivity, and DFT-derived descriptors. A key part of the role will be applying generative models directly to active drug discovery programs in close partnership with medicinal chemistry, while developing rigorous benchmarks to evaluate model performance and guide platform improvement. The ideal candidate is highly collaborative, scientifically rigorous, comfortable with hands-on data curation, and capable of independently driving projects in a fast-paced research environment.

Requirements

Ph.D. in machine learning, computational chemistry, chemical physics, computer science, applied mathematics, or a related discipline with 2+ years of industry experience, or M.S. degree with 6+ years of industry experience
Experience with quantum chemistry, DFT, electronic structure methods, or post-DFT descriptors.
Experience building molecular ML models including graph neural networks, geometric deep learning, equivariant architectures, diffusion models, or related approaches.
Experience applying generative models, molecular design models, or active learning workflows to drug discovery or chemistry optimization problems
Experience working closely with medicinal chemistry teams to prioritize compounds, interpret model outputs, and incorporate experimental feedback into model development
Experience developing rigorous model evaluation frameworks, benchmarks, and validation strategies for molecular ML or scientific machine learning applications and an ability to curate, clean, integrate, and analyze complex, large-scale scientific datasets from multiple sources
Proficiency with Python and modern ML frameworks such as PyTorch, PyTorch Geometric, DGL, or related tools
Experience with scalable data processing, model training, and analysis workflows for large scientific datasets
Ability to work closely with experimental scientists and translate biological and chemical questions into computational strategies
Excellent communication and cross-functional collaboration skills

Nice To Haves

Publications or preprints in, e.g., NeurIPS, ICML, ICLR, bioRxiv a strong plus.
Cheminformatics and molecular modeling toolkits such as RDKit, ORCA, Gaussian, Q-Chem, or related software is preferred
Experience with covalent chemistry, reaction modeling, structure-based design, or chemoproteomics data is a plus

Responsibilities

Develop, implement, and evaluate innovative machine learning methods for connecting (macro-)molecular quantum chemical features, reactivity modeling, covalent bond formation, and proteome-wide target engagement data
Design and implement rigorous benchmarks to evaluate model performance, including retrospective, prospective, and program-relevant validation strategies
Refine, fine-tune and apply Expedition’s foundational models to our drug discovery programs in close partnership with medicinal chemistry teams, supporting compound design, prioritization, and iterative learning from experimental results
Perform hands-on data curation, quality control, and dataset construction to ensure that models are trained and evaluated on high-quality, biologically and chemically meaningful data
Develop scalable featurization and modeling pipelines for large molecular datasets, including quantum chemistry outputs, conformer ensembles, protein-ligand interaction data, covalent reactivity data, and experimental chemoproteomics data
Collaborate closely with computational, chemistry, biology, and proteomics teams to translate platform data into actionable models for discovery programs
Partner with engineering teams to productionize modeling workflows, improve data infrastructure, and build self-serve capabilities for chemistry and discovery teams
Communicate technical findings, model performance, and scientific implications clearly across cross-functional teams