Senior LLM Training Engineer / RLHF Specialist (Team Lead)
RLHF
Led a team to produce RLHF annotations and high-quality training data for LLMs including AWS Nova. Developed structured training datasets, prompt engineering strategies, evaluation frameworks, and annotation guidelines for systematic human feedback and model performance improvement. Conducted extensive code quality reviews, evaluation of AI outputs, and established reproducible, quality-driven standards for AI-generated content.
• Created and maintained annotation methodologies for technical domains.
• Decomposed IaC workflows into step-based training sequences.
• Mentored engineers on best annotation and QA practices.
• Generated evaluation benchmarks for LLM output in code, cloud architecture, and deployment scripts.
Led a team to produce RLHF annotations and high-quality training data for LLMs including AWS Nova. Developed structured training datasets, prompt engineering strategies, evaluation frameworks, and annotation guidelines for systematic human feedback and model performance improvement. Conducted extensive code quality reviews, evaluation of AI outputs, and established reproducible, quality-driven standards for AI-generated content. • Created and maintained annotation methodologies for technical domains. • Decomposed IaC workflows into step-based training sequences. • Mentored engineers on best annotation and QA practices. • Generated evaluation benchmarks for LLM output in code, cloud architecture, and deployment scripts.
2025 - 2025