Key Responsibilities:
- Build canonical benchmark suite for antibody developability (aggregation, thermal stability, polyspecificity, self-interaction, viscosity, chemical liabilities, immunogenicity surrogates) and define multi-endpoint triage roll-up.
- Design sequence-aware privacy-preserving federated test sets using germline-, CDR-similarity-, and clonotype-based splits; account for shallow vs deep characterization asymmetry.
- Integrate and benchmark against public resources (SAbDab, OAS, TAP, Jain panel, FLAb, and emerging datasets).
- Develop cross-domain validation across IgG/bispecific/fragments, expression systems, and partner assay protocols; implement temporal-split and similarity-aware protocols for prospective deployment and drift.
- Partner on validation-relevant model design choices (feature/architecture, calibration, uncertainty quantification, combining endpoint predictions).
- Ensure statistical rigor (multiple testing, hierarchical structure) and provide confidence intervals; build reproducible MLOps pipelines and performance profiling; integrate validation with TuneLab (NVIDIA FLARE).
Basic Qualifications:
- PhD in a related field.
- 4+ years post-PhD in antibody discovery/engineering/developability data work.
- Experience with developability assays/data; numbering tools (ANARCI) and Kabat/Chothia/IMGT.
- ML validation protocol design for biological sequence data (similarity-aware splits; held-out test design).
Location/Travel: Indianapolis, San Francisco, or Boston; up to 10% travel.
Comp/Benefits (stated): $166,500β$266,200 + bonus eligibility and comprehensive benefits (e.g., 401(k), medical/dental/vision, flexible benefits, life insurance, time off, well-being).