Factulaity
In the Factuality project, I was responsible for verifying the accuracy of the information provided by the AI based on the user's prompt.
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
AI Training Specialist | Expert in Evaluation, Safety, and RLHF I am an experienced AI training specialist with a strong background in working with leading companies such as Populii, Outlier, Invisible, Mindrift, Telus, and Lionbridge. My work has spanned a wide range of AI training projects, including factuality assessment, comparative evaluation of response quality, and AI safety tasks. I also have hands-on experience with Reinforcement Learning from Human Feedback (RLHF) and have contributed extensively to evaluating and improving the quality of AI-generated conversations.
In the Factuality project, I was responsible for verifying the accuracy of the information provided by the AI based on the user's prompt.
In the Safety project, we tested the AI’s ability to resist generating harmful content, whether directed toward individuals or society. My role involved crafting prompts designed to challenge the AI and evaluating whether it would produce unsafe or inappropriate responses.
In the Cypher project, I was responsible for writing prompts that included specific user requests and then evaluating the AI's responses to ensure quality, relevance, and alignment with the intended objectives.
Bachelor's Degree, Pharmacy
AI Trainer
Pharmacist