AI-Driven Predictive Biology Postdoc

Lawrence Berkeley National Laboratory; San Francisco (CA); On-site; USD 92,000 - 103,000; Full time

Job summary

Lawrence Berkeley National Laboratory’s Environmental Genomics and Systems Biology division invites applications for an AI Predictive Biology Postdoctoral Fellow to advance genome- and protein-model-based function prediction within the KBase project. You will fine-tune and probe large models, leveraging diverse functional data and evaluating real biological tasks.

The role emphasizes model calibration, benchmarking, and dissemination of results, with an anticipated start date in October 2026 and

Qualifications

• PhD in Computational Biology, Bioinformatics, ML, CS, Statistics, or related field.
• Strong background in AI/ML and large-scale biological data.
• Experience adapting pretrained deep learning models to scientific tasks.
• Experience applying DL to biological sequences or omics data.
• Rigor in model evaluation, baselines, and statistics.
• Strong Python programming and PyTorch proficiency.
• Excellent communication and documentation skills.

Responsibilities

• Adapt and augment genome/protein foundation models for function prediction via fine-tuning, probing, or retrieval augmentation.
• Augment models with KBase functional signals and related data as training/conditioning context.
• Develop benchmarks linking model performance to gene function, fitness, phenotype, and pathways.
• Evaluate model calibration and uncertainty, and analyze failure modes.
• Deploy validated models and adapters with accessible documentation for researchers.
• Publish research findings, methods, and datasets; release evaluation code.

Skills

Python

PyTorch

Machine Learning

Computational Biology

Biological Data

Model Evaluation

Research Publications

Education

PhD in Computational Biology or related

Job description

Lawrence Berkeley National Laboratory’s Environmental Genomics and Systems Biology division invites applications for an AI Predictive Biology Postdoctoral Fellow to advance genome- and protein-model-based function prediction within the KBase project. You will fine-tune and probe large models, leveraging diverse functional data and evaluating real biological tasks.

The role emphasizes model calibration, benchmarking, and dissemination of results, with an anticipated start date in October 2026 and