Staff Scientist, Computational Biology & ML Data

Output Biosciences; Town of Tonawanda (NY); On-site; USD 120,000 - 190,000; Full time

Benefits offered by this job

Creativity encouraged

Autonomy in day-to-day work

Competitive salary and equity

Healthcare coverage

Job summary

Output Biosciences is building a biological reasoning model in the US and seeks a data-focused scientist to own data construction and benchmarking. You will craft training datasets, identify informative biological signals, and design benchmarks to ensure the model learns meaningful molecular biology.

You will collaborate with model researchers across modalities, develop data strategies, and stay current with biological data sources to drive real-world impact.

Qualifications

• PhD with 2+ years post-Doc or industry research in computational biology or related field.
• Deep understanding of molecular interactions and protein structure.
• Experience with large-scale biological datasets: sourcing, cleaning, integration, analysis.
• Strong Python programming and building scalable data pipelines.
• Understanding of data requirements for ML model training and evaluation.

Responsibilities

• Construct training datasets capturing protein-molecule interactions from diverse sources.
• Develop methods to extend training data beyond public databases using biological reasoning.
• Design benchmarks grounded in molecular phenomena to measure biologically meaningful learning.
• Collaborate with model researchers to determine what data signals to prioritize and how to sequence learning.
• Integrate data across scales and modalities to create coherent training data.

Skills

Python programming

Computational biology

Data processing

Biology data analysis

Education

PhD in computational biology or related

Job description

Output Biosciences is building a biological reasoning model in the US and seeks a data-focused scientist to own data construction and benchmarking. You will craft training datasets, identify informative biological signals, and design benchmarks to ensure the model learns meaningful molecular biology.

You will collaborate with model researchers across modalities, develop data strategies, and stay current with biological data sources to drive real-world impact.