ML Research Scientist, Co-Folding and Affinity

SandboxAQ

Research Scientist developing ML and physics-based models for drug and materials discovery. Contributing to the next-generation structure prediction and binding affinity models for a pioneering AI solutions company.

Posted 6/9/2026full-timeRemote • 🇺🇸 United StatesMid-LevelSenior💰 $112,000 - $210,000 per yearWebsite

Tech Stack

Tools & technologies

AWSAzureChaiCloudGoogle Cloud PlatformPythonPyTorch

About the role

Key responsibilities & impact

Implement, experiment with, and refine deep learning models for protein-ligand co-folding and structure prediction
Design and execute systematic evaluation pipelines to measure model performance against state-of-the-art methods and internal benchmarks
Collaborate with senior scientists and engineers to integrate validated models into production-ready drug discovery workflows
Employ computational and data analysis techniques to generate insights from structural and sequence datasets
Present research progress through internal scientific talks, technical write-ups, and contributions to peer-reviewed publications
Work closely with multidisciplinary teams to prototype and scale impactful solutions

Requirements

What you’ll need

Ph.D. in Computational Biology, Biophysics, Computer Science, Computational Chemistry, or a related field
Direct experience with protein structure prediction or protein-ligand co-folding methods (e.g., AlphaFold2/3, RoseTTAFold, Chai-1, Boltz, or comparable systems)
Experience developing, training, and validating deep learning models
Strong proficiency in Python and modern ML frameworks (PyTorch and/or JAX)
Demonstrated ability to design controlled experiments, interpret results critically, and iterate effectively on model development
Strong written and verbal communication skills; ability to work collaboratively in a fast-paced, multidisciplinary research environment
Active or recently completed postdoctoral research in co-folding, structure-based drug design, or closely related computational domain is highly desired.
Familiarity with binding affinity prediction methods
Authorship of publications or preprints in relevant venues (e.g., NeurIPS, ICML, Nature Methods, PLOS Computational Biology, bioRxiv).
Experience deploying ML workflows on public cloud infrastructure (e.g., GCP, AWS, or Azure) is a plus.
Exposure to generative models for protein/ligand design, active learning for data generation, foundation models for biomolecules, or QSAR/property prediction is a plus.
Familiarity with drug discovery workflows.

Benefits

Comp & perks

Comprehensive medical, dental, and vision coverage for employees and dependents with generous employer premium contributions
Retirement savings with company matching
Paid parental leave
Inclusive family-building benefits
Flexible paid time off
Company-wide seasonal breaks
Support for flexible work arrangements that enable sustainable performance
Opportunities for continuous learning and growth through on-the-job development, cross-functional collaboration, and access to internal learning and development programs

ATS Keywords

✓ Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

deep learning modelsprotein-ligand co-foldingstructure predictionPythonPyTorchJAXbinding affinity predictiongenerative modelsactive learningQSAR/property prediction

Soft Skills

strong written communicationstrong verbal communicationcollaborative workcritical interpretation of resultsiteration on model development

Certifications

Ph.D. in Computational BiologyPh.D. in BiophysicsPh.D. in Computer SciencePh.D. in Computational Chemistry