Freelance AI Workflow & LLM Evaluation Specialist
Worked as a Freelance AI Workflow & LLM Evaluation Specialist for platforms including TELUS, Appen, OneForma, and Outlier. Developed and evaluated structured workflows, prompt chains, and multi-step task decompositions to support LLM evaluation and prompt engineering. Analyzed AI-generated text responses for accuracy, consistency, and hallucination reduction across multiple environments. • Created and refined prompts to improve AI text outputs. • Evaluated AI system responses and identified logical errors and inconsistency patterns. • Utilized instruction tuning and prompt chaining for optimization. • Regularly used TELUS, Appen, and OneForma proprietary tools for workflow tasks.