AI/LLM Engineer
TextRLHF
As an AI/LLM Engineer, I contributed to the preparation and curation of supervised fine-tuning and reinforcement learning from human feedback datasets. I designed and crafted high-quality prompt–completion pairs to enhance LLM instruction-following and reasoning abilities. I maintained reproducible training environments to streamline annotation and model review workflows. • Developed and refined SFT, RLHF, and function-calling datasets across diverse domains. • Authored and evaluated few-shot and chain-of-thought prompt–completion formats. • Improved LLM output quality, reducing hallucinations and enhancing accuracy. • Enhanced annotation processes and environment setup efficiency for data labeling workflows.
As an AI/LLM Engineer, I contributed to the preparation and curation of supervised fine-tuning and reinforcement learning from human feedback datasets. I designed and crafted high-quality prompt–completion pairs to enhance LLM instruction-following and reasoning abilities. I maintained reproducible training environments to streamline annotation and model review workflows. • Developed and refined SFT, RLHF, and function-calling datasets across diverse domains. • Authored and evaluated few-shot and chain-of-thought prompt–completion formats. • Improved LLM output quality, reducing hallucinations and enhancing accuracy. • Enhanced annotation processes and environment setup efficiency for data labeling workflows.
2024 - Present