Member of Technical Staff, Interpretability

Output Biosciences; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Competitive salary and equity

Excellent medical, dental, and vision

Ownership of milestones

Creative, growth-focused culture

Job summary

Output Biosciences is building a pioneering biological reasoning model and seeks a candidate to advance interpretability across molecular scales. You will probe learned representations, design experiments, and produce tools that translate model internals into actionable biology insights.

You will work with teams across pretraining and generation to ensure interpretability informs model development. A PhD or equivalent experience plus publications are expected, with strong Python/PyTorch skills

Qualifications

• PhD in CS, ML, physics, math or related field with 2+ years post-doc or 5+ years hands-on research/engineering in interpretability.
• Strong publication record in top venues (NeurIPS, ICML, ICLR) focusing on mechanistic interpretability or related areas.
• Hands-on experience analyzing internal representations of large neural networks and designing revealing experiments.
• Proficiency in Python and PyTorch; experience with large models on GPU infrastructure.
• Ability to translate interpretability research into reusable, production-quality tools.

Responsibilities

• Develop methods to probe and reverse-engineer model representations across molecular scales.
• Design experiments to map model learned capabilities and biological knowledge.
• Build tools to extract interpretable outputs for downstream systems and scientists.
• Create visualizations or analyses that connect model internals to concrete biology concepts.
• Collaborate with pretraining and generation teams to integrate interpretability findings into model development.
• Own end-to-end pipeline from experiments to production-quality tools on distributed infrastructure.

Skills

Python

PyTorch

Experiment design

Model interpretability

GPUs

Version control

Education

PhD in CS / ML / Physics / Mathematics

Bachelor’s or Master’s with 5+ years research/engineering

Tools

Git

CUDA

Jupyter

Job description

Output has built a biological reasoning model that understands biology at the scale and complexity life actually operates. Our model independently learned the principles of molecular interactions, opening up drug treatments that were previously impossible. We're already generating therapies that traditional approaches cannot reach. The hardest problems in both AI and biology are being solved here, and there is room for you to own one.

Output is currently in stealth, operated by a team of repeat founders and biotech veterans with multiple exits in AI x Bio, and backed by top-tier VCs including Y Combinator.

You will continue developing methods to understand what our foundation model learns about biology, and build the tools that make it a glass box model. We believe that in biology, a model's reasoning must be visible. And the features you find are not just explanations: they expand what the model can do.

• You will continue developing our methods for probing and reverse-engineering the model's learned representations, understanding how it encodes biological information across molecular scales

• You will design and run experiments to identify and characterize capabilities, mapping what the model has learned about molecular interactions and biological function

• You will build methods to extract the model's biological understanding as explicit, usable outputs that downstream systems and researchers can act on

• You will create tools that connect model internals to meaningful biological concepts, making the model's reasoning interpretable to scientists and useful in practice

• You will work closely with the pretraining and generation teams, feeding interpretability findings back into model development to strengthen the capabilities you uncover

• You will own the full pipeline from probing experiments to production-quality interpretability tools, building robust systems on distributed infrastructure

About You

• You have a PhD in computer science, machine learning, physics, mathematics, or a related field with 2+ years of post-doctoral or industry research experience, or a Bachelor's or Master's degree with 5+ years of hands-on research and engineering experience in model interpretability or representation analysis

• You have a strong publication record at top-tier venues (e.g., NeurIPS, ICML, ICLR) with contributions to mechanistic interpretability, representation analysis, probing methods, or model understanding

• You have hands-on experience analyzing the internal representations of large neural networks, with demonstrated ability to design experiments that reveal what models have learned

• You are proficient in Python and PyTorch, and have experience working with large models on GPU infrastructure

• You have demonstrated the ability to take interpretability research from experiments to usable tools: you do not just analyze models, you build systems others can use

• You write production-quality code that is well-tested and maintainable, and you are comfortable working in shared codebases with version control and code review

• You think carefully about what constitutes evidence that a model has learned a concept, and you design experiments that distinguish real capabilities from artifacts

Bonus Points

• You have a background in chemistry, biology, computational biology, biophysics, or a related natural science

• You have experience interpreting ML models trained on scientific or biological data

• You have experience building visualization or analysis tools for model internals

• You have experience with multimodal models or representations that span multiple data types

• You have contributed to open-source machine learning projects

Our Values

Heart: We foster a culture of ownership. We are assembling a team of individuals who are passionate and take pride in their contributions.

Excellence: We have an unwavering commitment to excellence and continuously challenge ourselves to reach the highest standards.

Practicality: We value practicality and results-oriented thinking. We are committed to making a tangible impact on the lives of patients and the broader community.

Honesty: We place a high value on honesty and directness. We firmly believe in addressing issues as they arise, in an open and transparent manner.

Fun: We believe that life is too short to not have fun. Our goal is to create a workplace that is fun, engaging, rewarding and fulfilling.

What We Offer

• We encourage new and different ideas, creativity and contrarian thinking

• Healthy feedback focused environment to help you strive - leadership will have high expectations, regularly share constructive feedback, support you and help you grow, and welcome receiving feedback and ideas from you

• You own your day-to-day management. What we care about is that we all hit our milestones

• Competitive salary and equity in a growing, well-funded startup

• Excellent medical, dental, and vision coverage