Damilola A.

Key Skills

Software

Other

Top Subject Matter

AI safety evaluation

RLHF-style assessment

adversarial testing

Top Data Types

Text

Document

Top Task Types

Prompt + Response Writing (SFT)

Freelancer Overview

Self-directed adversarial testing and AI safety evaluation (across ChatGPT, Claude, Gemini, Kimi). Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Science, Tai Solarin University of Education. AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

LLM-assisted development for prompt engineering and AI workflow optimization

OtherPrompt + Response Writing (SFT)

Built and deployed production LLM-assisted applications to support prompt engineering and AI workflow optimization. Used Claude Code and GitHub Copilot in implementation workflows and delivered CI/CD-deployed web applications to enable iterative testing of prompts and model behavior. Translated hands-on LLM development experience into practical prompt engineering practices for evaluation and deployment contexts. • Deployed 2 production web applications • Developed with Claude Code and GitHub Copilot • Hosted on Vercel with CI/CD pipelines • Applied prompt engineering practices in iterative LLM-assisted development

2023 - Present

Self-directed adversarial testing and AI safety evaluation (across ChatGPT, Claude, Gemini, Kimi)

OtherText

Conducted AI safety and LLM output anomaly detection work using evidence-based documentation patterns translated from cybersecurity incident response. Applied structured severity ratings and comparative behavior analysis to evaluate model safety under adversarial conditions. Produced detailed written rationales and feedback-style submissions suitable for RLHF-style evaluation workflows. • Designed a self-directed adversarial testing suite • Documented 50+ test cases (jailbreaks, roleplay exploits, delimiter injection, context manipulation) • Created severity ratings and comparative model behavior matrices • Produced evaluation documentation aligned with RLHF annotation rationale needs

2022 - Present

Education

Work History