LLM Training & RLHF Reviewer (Pod Lead)
TextRLHF
This role involved conducting RLHF training and reviews for LLMs to improve AI-driven features. I was responsible for evaluating language model outputs, providing structured feedback, and optimizing system performance. The work was carried out for APPLE Inc. with a focus on enhancing the capabilities of conversational AI. • Conducted RLHF-based reviews for language model outputs
• Provided systematic feedback to improve AI response quality
• Managed LLM training for real-world deployed models
• Collaborated closely with cross-functional teams
This role involved conducting RLHF training and reviews for LLMs to improve AI-driven features. I was responsible for evaluating language model outputs, providing structured feedback, and optimizing system performance. The work was carried out for APPLE Inc. with a focus on enhancing the capabilities of conversational AI. • Conducted RLHF-based reviews for language model outputs • Provided systematic feedback to improve AI response quality • Managed LLM training for real-world deployed models • Collaborated closely with cross-functional teams
2025 - Present