Senior Lead / Pod Lead / AI Training Specialist, Turing
TextRLHF
Oversaw teams delivering calibrated textual datasets for LLM development, focusing on improving agent efficiency and performance. Directed dataset creation, calibration, and benchmark improvement tasks centered on reinforcement learning from human feedback (RLHF) and supervised fine-tuning (SFT). Contributed to high-profile AI systems for clients such as Apple Siri, Amazon AI, ServiceNow, and Microsoft Bing AI. • Led AI trainers in prompt-response data generation and evaluation
• Managed RLHF and SFT labeling projects end-to-end
• Developed processes for benchmark and calibration tasks
• Drove collaborative LLM training initiatives for advanced AI agents
Oversaw teams delivering calibrated textual datasets for LLM development, focusing on improving agent efficiency and performance. Directed dataset creation, calibration, and benchmark improvement tasks centered on reinforcement learning from human feedback (RLHF) and supervised fine-tuning (SFT). Contributed to high-profile AI systems for clients such as Apple Siri, Amazon AI, ServiceNow, and Microsoft Bing AI. • Led AI trainers in prompt-response data generation and evaluation • Managed RLHF and SFT labeling projects end-to-end • Developed processes for benchmark and calibration tasks • Drove collaborative LLM training initiatives for advanced AI agents
2024 - Present