Lead Software Engineer, EaglePoint AI – AI Prompt/Output Evaluation and Training Lead
Prompt Response Writing SFT
I lead the team responsible for designing prompts and ensuring AI outputs are accurate and useful for our users. This involves crafting and refining code-related prompts for AI coding agents and evaluating AI responses. My work improves the reliability of AI-generated code by continuously testing and updating prompt strategies.
• Designed system-level prompt workflows for internal AI agents.
• Tested and iteratively improved AI code generation output accuracy.
• Evaluated and rated responses from LLMs for overall quality and safety.
• Mentored team members to raise the standard of AI/LLM interaction and prompt engineering.
I lead the team responsible for designing prompts and ensuring AI outputs are accurate and useful for our users. This involves crafting and refining code-related prompts for AI coding agents and evaluating AI responses. My work improves the reliability of AI-generated code by continuously testing and updating prompt strategies. • Designed system-level prompt workflows for internal AI agents. • Tested and iteratively improved AI code generation output accuracy. • Evaluated and rated responses from LLMs for overall quality and safety. • Mentored team members to raise the standard of AI/LLM interaction and prompt engineering.
2026 - Present