Prompt Engineer and Al Response Evaluator (Contract)
Lablebox Inc. and Outlier Al
Nov 2024 - Current (1 year 4 months)
As a Prompt Engineer and AI Response Evaluator (Contract), I assisted in enhancing AI models for the RLFH and SFT project through prompt generation, including the creation of failure-inducing prompts, and evaluating responses in Mathematics, English, and Hindi. I reviewed, rated, and refined AI-generated outputs to improve model accuracy and contextual understanding. Additionally, I utilized my skills in report writing and data analysis to create detailed evaluations of prompts and responses related to political strategies, Indian government schemes, and economic policies, ensuring a comprehensive approach to model enhancement and contextual relevance.