Amie Twyford

Key Skills

Software

Mercor

Internal/Proprietary Tooling

Other

Labelbox

Scale AI

CVAT

Label Studio

Top Subject Matter

LLM Evaluation

AI Security

Agentic Workflow

Top Data Types

Computer Code Programming

Text

Document

Top Task Types

RLHF

Transcription

Prompt Response Writing SFT

Freelancer Overview

Independent Applied AI Researcher – Multi-Agent LLM Evaluation/Guardrail Testing. Brings 10+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Labelbox. Education includes Certificate, Stanford University (2025). AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

Independent Applied AI Researcher – Multi-Agent LLM Evaluation/Guardrail Testing

LabelboxText

Designed and tested multi-agent LLM evaluation frameworks for AI output reliability. Developed automated adversarial guardrail and prompt-injection stress testing procedures for agentic workflows. Created structured criteria for judging LLM responses in credibility models. • Designed evaluation metrics to assess LLM reliability for complex outputs • Automated adversarial attacks and guardrail tests for AI safety • Utilized tools like LangSmith and Labelbox for structured monitoring • Documented and analyzed results to guide AI security enhancements

Designed and tested multi-agent LLM evaluation frameworks for AI output reliability. Developed automated adversarial guardrail and prompt-injection stress testing procedures for agentic workflows. Created structured criteria for judging LLM responses in credibility models. • Designed evaluation metrics to assess LLM reliability for complex outputs • Automated adversarial attacks and guardrail tests for AI safety • Utilized tools like LangSmith and Labelbox for structured monitoring • Documented and analyzed results to guide AI security enhancements

2023 - Present

Education

Work History