Active/Registered Contributor, Outlier AI (Scale AI) – LLM Response Evaluation & Prompt Generation
Scale AIText
Contributed as an LLM response evaluator and prompt generator on AI training platforms. Performed RLHF tasks such as rating, comparing, and writing high-quality financial and general language prompts. Focused on domain-accurate evaluation and text annotation to enhance language model quality.
• Evaluated AI-generated responses for accuracy and relevance
• Generated financial and general writing prompts for training
• Participated in RLHF (Reward Modeling) workflows for LLMs
• Delivered feedback to improve and align AI model outputs
Contributed as an LLM response evaluator and prompt generator on AI training platforms. Performed RLHF tasks such as rating, comparing, and writing high-quality financial and general language prompts. Focused on domain-accurate evaluation and text annotation to enhance language model quality. • Evaluated AI-generated responses for accuracy and relevance • Generated financial and general writing prompts for training • Participated in RLHF (Reward Modeling) workflows for LLMs • Delivered feedback to improve and align AI model outputs
2023 - Present