Generative AI Practitioner (LLM Evaluation and Prompt Engineering)
Text
I conducted systematic evaluations of responses generated by large language models (LLMs) to assess quality and factual accuracy. I engineered prompts and documented structured feedback for generative AI workflows, contributing to prompt refinement and process reproducibility. I utilized tools including Claude Code, ComfyUI, and Flux models to automate quality review steps and maintain outputs consistency.
• Designed and executed model output evaluations focusing on language and content structure.
• Documented model behaviors and prompt templates for reproducibility.
• Automated evaluation workflows using Claude Code and internal tools.
• Collaborated across AI workflows for iterative quality improvements.
I conducted systematic evaluations of responses generated by large language models (LLMs) to assess quality and factual accuracy. I engineered prompts and documented structured feedback for generative AI workflows, contributing to prompt refinement and process reproducibility. I utilized tools including Claude Code, ComfyUI, and Flux models to automate quality review steps and maintain outputs consistency. • Designed and executed model output evaluations focusing on language and content structure. • Documented model behaviors and prompt templates for reproducibility. • Automated evaluation workflows using Claude Code and internal tools. • Collaborated across AI workflows for iterative quality improvements.
2023 - Present