Senior ML Researcher — Structural Biology & Drug Discovery

Accendum; United States; Remote; USD 130,000 - 180,000; Full time

Job summary

Accendum in the United States seeks a senior research leader to drive structure-based work at the intersection of generative chemistry, structural biology, and physical simulation. You own the path from a chosen target protein to a set of credible therapeutic candidates, partnering closely with engineering.

The role blends rigorous experimental design with a strong delivery bias: producing code senior scientists can defend and shipping workflows that engineering can operate.

Qualifications

• PhD in computational chemistry, biophysics, structural bioinformatics, CS, or adjacent ML field.
• Experience in modern structural or biomolecular ML (geometric DL, equivariant nets, protein-structure models).
• Strong Python and PyTorch (or JAX); proficient with RDKit, OpenMM or GROMACS, BioPython.
• Track record of published work, preprints, or shipped scientific software.
• Mature software engineering habits: version control, code review, testing, reproducibility.
• Excellent written and spoken English.

Responsibilities

• Lead protein-structure modelling and ligand-protein interaction studies.
• Design, run, and ship virtual screening campaigns over large libraries.
• Pair structural ML with MD and free-energy methods.
• Convert research prototypes into engineering-friendly pipelines.
• Communicate findings to mixed technical and scientific audiences.
• Mentor junior researchers and lift the experimental bar of the team.

Skills

Python

PyTorch

JAX

Geometric deep learning

Equivariant networks

Education

PhD in computational chemistry, biophysics, structural bioinformatics, computer science, or adjacent ML field

Tools

RDKit

OpenMM

GROMACS

BioPython

ESM/AlphaFold models

Job description

Role overview

A senior research position leading structure-based work at the intersection of generative chemistry, structural biology, and physical simulation. The researcher owns the path from a chosen target protein to a small set of credible therapeutic candidates end-to-end, partnering closely with engineering. The role combines rigorous experimental design with a strong delivery bias: research that produces code other senior scientists can defend.

Responsibilities

• Lead protein-structure modelling, ligand-protein interaction prediction, and binding-affinity studies for selected targets.
• Design, run, and ship virtual screening campaigns over large compound libraries with principled ranking and triage.
• Pair structural machine learning with physical simulation, including molecular dynamics and free-energy methods, when it improves outcomes.
• Convert research prototypes into pipelines that engineering can operate, with reviewer-friendly code.
• Communicate findings clearly to mixed technical and scientific audiences and engage with external collaborators.
• Mentor junior researchers and lift the experimental bar of the team.

Requirements

• PhD in computational chemistry, biophysics, structural bioinformatics, computer science, or an adjacent machine learning field.
• Demonstrated work in modern structural or biomolecular ML, such as geometric deep learning, equivariant networks, protein-structure models, or generative chemistry.
• Strong Python and PyTorch (or JAX), with fluency in libraries like RDKit, OpenMM or GROMACS, BioPython, and ESM- or AlphaFold-class models.
• A track record of published work, preprints, or shipped scientific software.
• Mature software-engineering habits: version control, code review, testing, and reproducibility.
• Excellent written and spoken communication in English.

Benefits and work setup

• Compute and tooling appropriate to the problem at hand.
• Conference, publication, and collaboration support.
• Flexible remote work across European and Americas time zones.