Sarah-Jane Williams

Key Skills

Software

Mercor

Top Subject Matter

AI Model Testing and Evaluation

AI Security and LLM Evaluation

Legal Services & Contract Review

Top Data Types

Text

Document

Top Task Types

Prompt Response Writing SFT

Red Teaming

Freelancer Overview

Annotator / Model Tester / Annotator. Brings 24+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Mercor and Innodata. Education includes Certificate in Teaching English as a Foreign Language, Greenway Thailand (2010) and Postgraduate Diploma in Legal Practice at the Bar, Manchester Metropolitan University (2009). AI-training focus includes data types such as Text and labeling workflows including Prompt + Response Writing (SFT) and Red Teaming.

Labeling Experience

Annotator / Model Tester / Annotator

MercorTextPrompt Response Writing SFT

As a freelance Annotator and Model Tester for Mercor, I created and tested hundreds of prompts to benchmark and refine AI model outputs. I maintained high accuracy and throughput in large-scale annotation workflows. My work supported WideSearch and BrowseComp benchmarking projects with a focus on quality and consistency. • Developed effective prompts for LLM evaluation • Collaborated in refining AI behavior • Performed large-scale annotation tasks • Maintained excellent accuracy metrics

As a freelance Annotator and Model Tester for Mercor, I created and tested hundreds of prompts to benchmark and refine AI model outputs. I maintained high accuracy and throughput in large-scale annotation workflows. My work supported WideSearch and BrowseComp benchmarking projects with a focus on quality and consistency. • Developed effective prompts for LLM evaluation • Collaborated in refining AI behavior • Performed large-scale annotation tasks • Maintained excellent accuracy metrics

2025 - Present

Prompt Engineer / Annotator / Red Teamer

TextRed Teaming

As a freelance Prompt Engineer and Annotator at Innodata, I crafted adversarial prompts and analyzed AI responses to uncover vulnerabilities in large language models. I participated in model red teaming, leading to critical system improvements. I also performed quality control for culture-focused prompts and evaluated tool triggering during production testing. • Identified weaknesses in AI output through adversarial testing • Contributed to prompt quality assurance and improvement • Conducted evaluation of tool use within LLM responses • Benchmarked search relevance for user experience optimization

As a freelance Prompt Engineer and Annotator at Innodata, I crafted adversarial prompts and analyzed AI responses to uncover vulnerabilities in large language models. I participated in model red teaming, leading to critical system improvements. I also performed quality control for culture-focused prompts and evaluated tool triggering during production testing. • Identified weaknesses in AI output through adversarial testing • Contributed to prompt quality assurance and improvement • Conducted evaluation of tool use within LLM responses • Benchmarked search relevance for user experience optimization

2024 - Present

Education

Work History