Don Orr

a i Prompt Injection Engineer @GE HealthCare

Richmond, VA, US

Safeguard AI systems by identifying, simulating, and mitigating prompt injection vulnerabilities through adversarial testing and red teaming exercises on large language models. This involves developing robust defenses, such as input validation, model sandboxing, and threat detection pipelines, to prevent malicious manipulations that could lead to data leakage or unauthorized behaviors in generative AI applications.

Liberty University

Bachelor's degree, Computer and Information Systems Security/Information Assurance