Computational Chemist

Topos Bio; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Topos Bio is seeking a Computational Chemist in San Francisco to generate novel molecules for diverse targets and work closely with AI researchers and experimental scientists.

You will develop scalable workflows, run MD simulations with enhanced sampling, and build data pipelines for large-scale predictions, while collaborating across teams to deliver robust computational insights.

Qualifications

• PhD in Computational Biophysics, Computational Chemistry, or a related field.
• Experience with molecular modeling, simulation, and generative drug design.
• Proficiency with common computational biophysics software (AMBER, GROMACS, OpenMM, PLUMED, Schrödinger, OpenEye).
• Strong coding in Python and familiarity with HPC/cloud environments.

Responsibilities

• Develop scalable workflows to generate and screen thousands of potential drug candidates.
• Design and run molecular dynamics simulations, applying enhanced sampling methods.
• Engineer and optimize data pipelines for large-scale simulations and structure-based predictions.
• Build and optimize cheminformatics pipelines for compound filtering and similarity search.
• Collaborate with AI researchers to incorporate simulation data into model training and inference.
• Bridge scientific rigor with practical results in accurate and efficient computational protocols.
• Communicate technical nuances to cross-functional teams and partners.
• Stay up to date with breakthroughs in computational chemistry, generative models, and molecular simulation.

Skills

Molecular modeling

Molecular dynamics simulations

Generative drug design

Data pipelines

Python

HPC / cloud computing

Communication skills

Education

PhD in Computational Biophysics

Tools

AMBER

GROMACS

OpenMM

PLUMED

Schrödinger

OpenEye

Job description

Topos Bio

At Topos Bio, we’re pioneering drug discovery for intrinsically disordered proteins—targets that have eluded conventional approaches in neurodegeneration, oncology, and cardiometabolic disease.

We’re seeking a Computational Chemist to help generate novel molecules for a variety of targets and collaborate closely with AI researchers and experimental scientists.

What you will do

• Develop scalable workflows to generate and screen thousands of potential drug candidates

• Design and run molecular dynamics simulations, applying enhanced sampling methods to characterize protein-ligand binding and conformational dynamics

• Engineer and optimize data pipelines that handle large-scale molecular simulations and structure-based predictions

• Build and optimize cheminformatics pipelines for compound filtering, property prediction, fingerprint-based similarity search, and chemical space analysis

• Collaborate with AI researchers to incorporate simulation data into model training and inference pipelines

• Bridge scientific rigor with practical results, ensuring computational protocols are both accurate and efficient

• Communicate technical nuances to cross-functional teams, fostering a shared understanding of capabilities and limitations

• Stay up to date with the latest research and breakthroughs in computational chemistry, generative models, and molecular simulation

• Lead external scientific presentations to pharmaceutical partners; Communicate the team’s computational approaches for both technical audiences and business partners

What we are looking for

• PhD in Computational Biophysics, Computational Chemistry, or a related field

• Experience with molecular modeling, simulation, and generative drug design

• Proficiency with common computational biophysics software (e.g. AMBER, GROMACS, OpenMM, PLUMED, Schrödinger, OpenEye)

• Strong background in cheminformatics: molecular fingerprints, QSAR/QSPR, property prediction, scaffold analysis, cheminformatics libraries (e.g., RDKit, OpenBabel)

• Expert coding in at least one language (Python preferred)

• Familiarity with HPC cluster or cloud computing environments, containerization, and workflow orchestration

• Strong communication skills, with the ability to present complex ideas in clear terms

Preferred

• Experience integrating machine learning techniques for molecular generation

• Background in quantum chemistry methods (DFT, ab initio) and its application to biomolecular systems

• Exposure to early-stage drug discovery programs, from target identification to lead optimization