Scientist, AI/ML — Antibody Developability
Ginkgo Bioworks · CA
ResearchCompany career page
The apply link worked recently (not employer-confirmed).
Role summary
Ginkgo Bioworks seeks a scientist to develop and validate machine learning models predicting antibody developability using biophysical data and protein embeddings. The role bridges experimental high-throughput assay platforms with computational design, requiring expertise in applied ML and protein biophysics.
What they're looking for
- Ph.D. in Computational Biology, Bioinformatics, ML, Biophysics, or related quantitative field
- Proficiency in Python and scientific computing (NumPy, pandas, PyTorch/TensorFlow)
- Demonstrated supervised learning experience on biological datasets with cross-validation expertise
- Knowledge of protein representations including PLM embeddings (ESM, AbLang) and structural features
- Ability to analyze biophysical data for signal-to-noise ratios and experimental dynamic range
- Strong communication skills across multidisciplinary teams managing concurrent objectives
What you'll be doing
- Develop and validate predictive models for antibody developability using multiple feature types
- Implement leakage-aware evaluation frameworks for rigorous assessment of small-scale datasets
- Evaluate cross-format transferability and deploy data-efficient training strategies
- Perform quality control on biophysical assay data to identify outliers and ensure data integrity
- Maintain automated pipelines and disseminate findings through manuscripts and presentations
Privacy & handoff
This role links to Ginkgo Bioworks's own application system. RoleLantern records your interest and checks the link, but the application happens on the employer's site and status updates may not come back to us. Clicking apply does not mark you as applied automatically.