R
Red Deer polytechnic in artificial intelligence and data analytics program
Degree not specified
Not specified
Not specified
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No software listed
Conducted adversarial red-teaming of large language models and AI agents, identifying vulnerabilities through jailbreaks, prompt injections, misuse scenarios while generating datasets to improve model safety and robustness for enterprise customers for 6 months. Generate high-quality human evaluation data by annotating response strengths, areas for improvement, and factual inaccuracies
Degree not specified
AI Trainer (Adversarial AI Testing and RLFH annotation)