AI Engineer and Senior Auditor (Oracle Tier) at Outlier
I am engaged as an AI Engineer focusing on LLM training and Reinforcement Learning from Human Feedback (RLHF) at Outlier. My responsibilities include evaluating, rating, and correcting code and mathematical responses to improve model accuracy. I ensure model outputs are aligned with quality standards and subject-matter expectations. • Conduct RLHF labeling on mathematical and programming responses • Audit and correct outputs for alignment and high fidelity • Collaborate with teams to deliver over 100 RLHF and evaluation projects • Leverage analytical skills in text and code evaluation