Desmond Sleigh

Key Skills

Software

Scale AI

Other

Top Subject Matter

AI Safety and LLM Evaluation

AI Workflow QA and Evaluation

AI Safety Red Teaming and Evaluation

Top Data Types

Text

Document

Top Task Types

Red Teaming

Freelancer Overview

AI Operations Analyst (GenAI). Brings 12+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Scale AI, Tailored, and Other. Education includes Bachelor of Science, Indiana Wesleyan University. AI-training focus includes data types such as Text and labeling workflows including Red Teaming, Evaluation, and Rating.

Labeling Experience

AI Safety Red Teaming | Contract Consultant

OtherTextRed Teaming

As a contract consultant, I generated adversarial prompts targeting edge cases in AI safety classifiers. I applied category and severity labels grounded in policy guidelines and authored concise rationales for decisions. I performed high-volume labeling and reviewed peer submissions for accuracy and consistency. • Designed and executed adversarial prompt-based red teaming for safety classifiers. • Applied structured safety classification and severity scoring per requirements. • Composed policy-grounded rationales to justify classification choices. • Reviewed labeling outputs of others to ensure consistency and quality.

As a contract consultant, I generated adversarial prompts targeting edge cases in AI safety classifiers. I applied category and severity labels grounded in policy guidelines and authored concise rationales for decisions. I performed high-volume labeling and reviewed peer submissions for accuracy and consistency. • Designed and executed adversarial prompt-based red teaming for safety classifiers. • Applied structured safety classification and severity scoring per requirements. • Composed policy-grounded rationales to justify classification choices. • Reviewed labeling outputs of others to ensure consistency and quality.

2025 - Present

AI Operations Analyst (GenAI)

Scale AITextRed Teaming

I led structured red-teaming and evaluation cycles for large language models at Scale AI. My responsibilities included designing adversarial prompts, applying category and severity labels, and generating policy-based rationales. I conducted these tasks at scale, ensuring consistency and accuracy across large evaluation queues. • Designed adversarial prompts to target edge-case failure modes in LLMs. • Applied category and severity classification labels along safety taxonomies. • Authored concise rationales supporting each classification decision. • Validated peer submissions to maintain high-quality data labeling outputs.

I led structured red-teaming and evaluation cycles for large language models at Scale AI. My responsibilities included designing adversarial prompts, applying category and severity labels, and generating policy-based rationales. I conducted these tasks at scale, ensuring consistency and accuracy across large evaluation queues. • Designed adversarial prompts to target edge-case failure modes in LLMs. • Applied category and severity classification labels along safety taxonomies. • Authored concise rationales supporting each classification decision. • Validated peer submissions to maintain high-quality data labeling outputs.

2025 - Present

AI Operations Specialist

Text

As an AI Operations Specialist, I operated and quality checked AI-driven content and data workflows. I embedded QA checkpoints and monitored the accuracy and performance of generative AI outputs. I contributed to delivering high-quality data used for model fine-tuning and adoption recommendations. • Implemented QA processes for generative AI content output. • Evaluated AI tools and recommended for production use based on performance. • Ensured operational fidelity of AI-generated data for multiple business use cases. • Supported high-volume evaluation and verification tasks for AI outputs.

As an AI Operations Specialist, I operated and quality checked AI-driven content and data workflows. I embedded QA checkpoints and monitored the accuracy and performance of generative AI outputs. I contributed to delivering high-quality data used for model fine-tuning and adoption recommendations. • Implemented QA processes for generative AI content output. • Evaluated AI tools and recommended for production use based on performance. • Ensured operational fidelity of AI-generated data for multiple business use cases. • Supported high-volume evaluation and verification tasks for AI outputs.

2023 - 2025

Education

Work History