Computational Biologist (AI/Bio)

TL;DR

Computational Biologist (AI/Bio): Constructing biological training datasets and evaluation benchmarks for a biological reasoning model with an accent on molecular interactions, protein structure, and heterogeneous data integration. Focus on designing biologically rigorous training signals, preventing data leakage, and building evaluation strategies that measure generalization to real molecular problems.

Location: New York HQ or the Bay Area

Salary: $150,000–$350,000 plus equity

Company

hirify.global is a stealth-stage AI and biotech startup developing biological reasoning models for drug discovery.

What you will do

• Construct large-scale training datasets describing protein and molecular interactions from diverse biological sources.
• Develop biological and chemical reasoning methods to generate training signals beyond existing public databases.
• Design benchmarks, dataset splits, and evaluation strategies that measure meaningful molecular capabilities and prevent leakage.
• Define data strategies with model researchers, including signal prioritization and learning sequences across modalities.
• Integrate heterogeneous experimental and computational data across biological scales.
• Monitor biological databases, experimental methods, and emerging sources of training data.

Requirements

• PhD in computational biology, biophysics, structural biology, chemistry, biochemistry, or a related field, plus 2+ years of postdoctoral or industry research experience, or equivalent expertise.
• Deep understanding of molecular interactions, protein structure, and molecular-level biological data.
• Experience sourcing, cleaning, integrating, and analyzing large-scale heterogeneous biological or molecular datasets.
• Strong Python programming skills and experience building computational data-processing pipelines.
• Understanding of machine-learning training data requirements, including coverage, quality, balance, and evaluation rigor.

Nice to have

• Experience with structure prediction, molecular docking, or virtual screening.
• Experience training or evaluating machine-learning models on molecular or biological data.
• Publications in computational biology, bioinformatics, or molecular informatics.
• Background in cheminformatics or molecular data analysis.
• Experience with protein or molecular language models.

Culture & Benefits

• Ownership-driven culture with high standards and emphasis on meaningful contributions.
• Open, direct feedback focused on growth and continuous improvement.
• Autonomy over day-to-day work, with focus on achieving shared milestones.
• Competitive salary and equity at a growing, well-funded startup.
• Medical, dental, and vision coverage.