SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 130,600 - 183,800 / annual
Ginkgo Bioworks' Datapoints team is seeking a Scientist to develop and benchmark machine learning models that predict and design antibody developability. You will work at the intersection of the PROPHET-Ab high-throughput biophysical platform and the computational models it enables, leveraging both newly generated customer datasets and the GDPa public dataset series (clinical IgGs, sequence-diverse natural IgGs, bispecifics, VHH-Fcs). The role involves cross-format prediction and generative design campaigns.
Key responsibilities include:
- Develop and validate predictive models for developability using protein language model (PLM) embeddings, structural features, and physicochemical descriptors
- Implement leakage-aware evaluation frameworks for rigorous performance assessment on small-scale datasets
- Evaluate cross-format transferability (IgG to VHH-Fc, bispecifics) and deploy data-efficient training strategies
- Perform rigorous quality control on biophysical assay data to identify outliers and maintain data integrity for modeling
- Maintain and develop automated pipelines to ensure reproducibility and facilitate technical reporting
- Disseminate findings through technical reviews, peer-reviewed manuscripts, and external scientific presentations
This computational role requires deep understanding of biophysical assay measurements, noise characteristics, and rigorous evaluation strategies for small-scale datasets. You will work across multidisciplinary teams integrating experimental and computational design.
REQUIREMENTS:
Required:
- Ph.D. in Computational Biology, Bioinformatics, Machine Learning, Biophysics, or related quantitative field with emphasis on applied ML
- Proficiency in Python and the scientific computing stack (NumPy, pandas, PyTorch/TensorFlow)
- Demonstrated experience in supervised learning on biological datasets, including expertise in cross-validation and bias mitigation
- Knowledge of protein representations, including PLM embeddings (e.g., ESM, AbLang) and structural featurization
- Ability to analyze biophysical data with respect to signal-to-noise ratios and experimental dynamic range
- Effective communication across multidisciplinary teams and ability to manage concurrent technical objectives
Preferred:
- Familiarity with antibody formats (VHH, scFv), therapeutic developability liabilities, and relevant characterization assays
- Experience with state-of-the-art supervised techniques such as tabular foundation models
- Exposure to generative sequence modeling, diffusion models, and reward-based steering
- Experience with protein structure prediction (AlphaFold, ABodyBuilder) and surface patch analysis
- Prior engagement with high-throughput experimental design and collaborative data generation
- Record of scientific publication and software engineering fundamentals (Git, testing, cloud compute)
