Research Scientist, Mechanistic Interpretability (AI)

TL;DR

Research Scientist, Mechanistic Interpretability (AI): Developing methods and production tools that reveal how a biological foundation model represents molecular interactions and biological function with an accent on mechanistic interpretability, representation analysis, and scientific model understanding. Focus on designing probing experiments, extracting usable biological concepts from model internals, and connecting interpretability findings to distributed model development infrastructure.

Location: New York HQ or Bay Area, United States

Salary: $150,000–$350,000 plus equity

Company

hirify.global is a stealth-stage biotech startup developing biological foundation models for discovering previously inaccessible drug treatments.

What you will do

• Develop methods for probing and reverse-engineering learned representations across molecular scales.
• Design and run experiments to characterize model capabilities and biological knowledge.
• Build methods that extract explicit biological insights for researchers and downstream systems.
• Create visualization and analysis tools that connect model internals with meaningful biological concepts.
• Collaborate with pretraining and generation teams to improve model capabilities.
• Own the pipeline from research experiments to production-quality tools on distributed infrastructure.

Requirements

• PhD in computer science, machine learning, physics, mathematics, or a related field with 2+ years of postdoctoral or industry research experience, or a bachelor's/master's degree with 5+ years of relevant research and engineering experience.
• Strong publication record at top-tier venues such as NeurIPS, ICML, or ICLR.
• Hands-on experience analyzing internal representations of large neural networks and designing experiments to evaluate learned concepts.
• Proficiency in Python and PyTorch, with experience working with large models on GPU infrastructure.
• Ability to convert interpretability research into usable, production-quality tools.
• Strong software engineering practices, including testing, maintainability, version control, and code review.

Nice to have

• Background in chemistry, biology, computational biology, biophysics, or a related natural science.
• Experience interpreting models trained on scientific or biological data.
• Experience building visualization or analysis tools for model internals.
• Experience with multimodal models or open-source machine learning projects.

Culture & Benefits

• Ownership-driven culture with high standards and a focus on tangible impact.
• Direct, transparent feedback and support for professional growth.
• Autonomy over day-to-day work with an emphasis on achieving milestones.
• Competitive salary, equity, and a well-funded startup environment.
• Medical, dental, and vision coverage.