This page prioritizes high-confidence claims from program descriptions and technical notes. It avoids ornamental inflation and preserves boundary between documented work and later synthesis.
Core role
Senior AI researcher working across tactical cybersecurity, code vulnerability modeling, and distributed edge inference. Responsibilities spanned modeling, data pipelines, evaluation design, and deployment-minded integration.
Program snapshots
- T-UEBA: tactical UEBA for Zero Trust conditions using temporal-heterogeneous behavior modeling and adaptive risk calibration.
- DL-PATCHER: automated vulnerability repair workflows over code corpora with transformer-family modeling and curation-heavy fine-tuning.
- SpHyRE-Net: low-SWaP anomaly-focused modeling for constrained edge environments.
- DAICON: distributed AI execution over heterogeneous tactical nodes with resilience under ad hoc networking constraints.
- DEVIS: embedded vulnerability detection in binaries with ML-assisted path prioritization.
Technical through-line
Across programs, the design invariant was constant: combine expressive learned components with explicit operational boundaries so systems stay calibratable, inspectable, and deployable under stress.
Patent context
Co-inventor: Automated Bug Fixing Using Deep Learning Including Pre-training and Fine-tuning, U.S. application 18/375,839 (Geddes, Mabie, McGraw).