Lead Generative ML Scientist, Molecular Design

Output Biosciences; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Competitive salary

Equity

Medical coverage

Dental coverage

Vision coverage

Ownership culture

Job summary

Output Biosciences in San Francisco seeks a leader to design and implement generative molecular models, spanning small molecules to biological data, from research to trained systems.

You will own end-to-end training on multi-GPU clusters, develop architectures, and evaluate outputs for biological relevance and novelty, with a track record of publications.

Join a well-funded startup culture focused on ownership, excellence and practical impact.

Qualifications

• PhD with 2+ years post-doctoral or industry research experience, or Bachelor’s/Master’s with 5+ years hands-on research in generative modeling.
• Strong publication record in generative methods (NeurIPS, ICML, ICLR)
• Hands-on experience designing, building, and training deep generative models, including novel architectures or training objectives
• Proficient in Python and PyTorch, with experience training models on distributed multi-GPU infrastructure
• Own the full research-to-training pipeline: design, train, and ship models
• Production-quality code, well-tested and maintained, in shared codebases with version control and code review
• Rigorous experimentalist with careful evaluation, systematic experimentation, and data-driven conclusions

Responsibilities

• Design and build generative architectures for molecular data spanning multiple modalities (small molecules, peptides, mini proteins)
• Develop training approaches that learn from diverse biological signals and ensure novel structures
• Build methods for controllable generation to meet specified biological properties and chemical constraints
• Integrate biological reasoning from the foundation model into the generative pipeline
• Own training end-to-end: experiment design, distributed training on multi-GPU clusters, hyperparameter optimization
• Design evaluation frameworks to measure biological meaningfulness, structural validity, and novelty

Skills

Python

PyTorch

Distributed training

Experiment design

Publications

Education

PhD in computer science, ML, physics, mathematics, or related field

Bachelor's or Master's with 5+ years hands-on research

Job description

Output Biosciences in San Francisco seeks a leader to design and implement generative molecular models, spanning small molecules to biological data, from research to trained systems.

You will own end-to-end training on multi-GPU clusters, develop architectures, and evaluate outputs for biological relevance and novelty, with a track record of publications.

Join a well-funded startup culture focused on ownership, excellence and practical impact.