Machine Learning Research Scientist, Interpretability

Output Biosciences • New York, NY

7d

About The Position

Join our team and help build the world's first biological reasoning model. Work with us to build generative foundational models that decode biological systems across scales — from molecules to organisms — enabling us to predict, understand, and program living systems in ways never before possible.
Output Biosciences is currently in stealth, operated by a team of repeat founders and biotech veterans with multiple exits in AI and biology, and backed by top VCs including Y Combinator.
As a Machine Learning Research Scientist, Interpretability, you'll work alongside our founders and team members to develop AI systems capable of processing and reasoning across multiple biological data modalities simultaneously.
You will develop specialized methods for understanding our biological reasoning models, reverse-engineering how they represent and process complex biological information.
You will design and conduct experiments to uncover interpretable features across biological scales.
You will address unique challenges in biological model interpretation, such as disentangling the multi-scale, hierarchical representations of biological systems
You will build biology-specific visualization tools that can map model activations to meaningful biological concepts.

Requirements

• You have a Bachelor's degree in Computer Science, Computer Engineering, Mathematics, Physics, or a relevant technical field.
• You have a PhD with 2 years of research experience, or a Bachelor's degree with 4+ years of research or industry experience in Deep Learning, Artificial Intelligence, or other relevant fields.
• You have a strong publication record in top-tier AI conferences or journals (e.g., NeurIPS, ICML, ICLR).
• You are proficient in Python and have expertise in at least one major deep learning framework (PyTorch, TensorFlow, or JAX).
• You have excellent problem-solving skills and the ability to quickly adapt to new challenges.
• You exhibit a proactive approach to problem-solving, thinking beyond the specific task, taking ownership of challenges, and taking pride in solving them.
• You have a mature mindset in ambiguous situations, helping to frame questions and seek clarity while making decisions in the face of uncertainty.
• You have excellent communication skills and can clearly articulate complex technical concepts.
• You are motivated by making a real impact and are committed to tackling problems of significant consequence with determination and creativity.

Nice To Haves

• You have experience applying machine learning to biological or chemical problems.
• You have knowledge of physics, molecular biology, chemistry, computational biology, bioinformatics, cheminformatics, or related fields.
• You have experience with multi-modal learning.
• You have contributed to open-source machine learning projects/
• You have experience in developing efficient code in C/C++.

Responsibilities

• Develop specialized methods for understanding our biological reasoning models, reverse-engineering how they represent and process complex biological information.
• Design and conduct experiments to uncover interpretable features across biological scales.
• Address unique challenges in biological model interpretation, such as disentangling the multi-scale, hierarchical representations of biological systems
• Build biology-specific visualization tools that can map model activations to meaningful biological concepts.

Benefits

• 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

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level