Member of the Technical Staff, Biological Data

Output Biosciences • New York, NY

4d • $150,000 - $250,000 • Remote

About The Position

Output has developed a biological reasoning model capable of understanding biology at a scale and complexity previously unattainable, leading to the development of novel drug treatments. The company is currently in stealth mode, founded by experienced entrepreneurs in AI and biotech, and backed by prominent venture capitalists. This role is crucial as the individual will be responsible for the data that trains the company's models. It requires a deep understanding of molecular biology, including the content, implications, and gaps within biological data sources. The quality and scope of training data are paramount to the model's learning capabilities, and the biological insight behind data construction differentiates a reasoning model from one that merely memorizes.

Requirements

• PhD in computational biology, biophysics, structural biology, chemistry, biochemistry, or a related biological field with 2+ years of post-doctoral or industry research experience, or equivalent depth through a combined biology and computational background.
• Deep understanding of molecular interactions, protein structure, and biological data at the molecular level, grounded in first principles.
• Experience working with large-scale biological or molecular datasets, including sourcing, cleaning, integrating, and analyzing heterogeneous data.
• Strong programming skills in Python and comfort building computational pipelines for data processing at scale.
• Understanding of what machine learning models require from training data: coverage, quality, balance, and evaluation rigor.
• Approach to data construction as a research problem, carefully considering data meaning, signal, and absence.

Nice To Haves

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

Responsibilities

• Construct training datasets that capture protein and molecule interactions, drawing from diverse biological data sources and enhancing them with an understanding of molecular principles.
• Develop methods to expand training data beyond public databases by using biological and chemical reasoning to create new training signals where data is sparse or absent.
• Design benchmarks grounded in real molecular phenomena to measure whether models have learned biologically meaningful capabilities rather than statistical shortcuts.
• Develop data strategies in collaboration with model researchers, defining data sources, prioritizing biological signals, and sequencing learning across modalities.
• Design approaches for integrating data across biological scales and modalities, creating coherent training data from heterogeneous experimental and computational sources.
• Design rigorous splitting and evaluation strategies to prevent data leakage and ensure model capabilities generalize to real biological problems.
• Stay current with biological data sources, experimental methods, and molecular databases to continuously identify new sources of training signal.

Benefits

• Competitive salary and equity in a growing, well-funded startup.
• Excellent medical, dental, and vision coverage.
• Encouragement of new and different ideas, creativity, and contrarian thinking.
• Healthy feedback-focused environment with constructive feedback, support, and growth opportunities.
• Ownership of day-to-day management, with a focus on hitting milestones.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: Ph.D. or professional degree