Senior AI Research Engineer - RLHF Optimization and LLM Training
TextRLHF
I led RLHF pipeline optimization for safer and more aligned language models. I directed improvements in human feedback loops to enhance LLM fine-tuning. Model performance and safety were significantly boosted through AI training iterations.
• Led a cross-functional team for RLHF optimizations
• Improved human-AI alignment processes
• Architected distributed training for LLMs
• Enhanced LLM safety via human feedback
I led RLHF pipeline optimization for safer and more aligned language models. I directed improvements in human feedback loops to enhance LLM fine-tuning. Model performance and safety were significantly boosted through AI training iterations. • Led a cross-functional team for RLHF optimizations • Improved human-AI alignment processes • Architected distributed training for LLMs • Enhanced LLM safety via human feedback
2024 - 2025