AI Lab Lead — RLHF & LLM Training (Self-hosted Lab, Soi Technology Solutions)
TextRLHF
Managed a private AI lab focused on self-hosted large language model (LLM) inference and reinforcement learning from human feedback (RLHF). Conducted experiments with RLHF workflows for model evaluation and custom fine-tuning, leveraging Nvidia H100 GPU resources. Led research initiatives in AI training and model assessment using proprietary pipelines.
• Built and refined RLHF data annotation and evaluation processes.
• Oversaw hardware-aware AI model fine-tuning operations.
• Designed custom evaluation protocols for LLM performance.
• Utilized internal/proprietary tooling for annotation and feedback implementation.
Managed a private AI lab focused on self-hosted large language model (LLM) inference and reinforcement learning from human feedback (RLHF). Conducted experiments with RLHF workflows for model evaluation and custom fine-tuning, leveraging Nvidia H100 GPU resources. Led research initiatives in AI training and model assessment using proprietary pipelines. • Built and refined RLHF data annotation and evaluation processes. • Oversaw hardware-aware AI model fine-tuning operations. • Designed custom evaluation protocols for LLM performance. • Utilized internal/proprietary tooling for annotation and feedback implementation.
2025 - Present