Bolaji J.

Key Skills

Software

Other

Top Subject Matter

LLM testing and prompt engineering (hallucination detection and evaluation)

Technical/academic writing used as ground-truth content for AI training

Top Data Types

Text

Image

Video

Top Task Types

Text Generation

Question Answering

Object Detection

Classification

Segmentation

Point/Key Point

Text Summarization

Transcription

Evaluation/Rating

Freelancer Overview

AI Model Evaluator & Prompt Engineer — Arena AI (LLM Arena). Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Certificate in AI Prompt Engineering Specialization, Coursera (2025) and Certificate in Anthropic AI Learning Resources and Claude Courses, Anthropic / Claude Courses (2025). AI-training focus includes data types such as Text and labeling workflows including Text Generation, Evaluation, and Rating.

Labeling Experience

Technical Writer & Content Specialist — Freelance / Self-Employed

OtherText

Produced fact-checked educational and technical written content that supports AI training and evaluation workflows requiring clear, accurate ground truth narratives. Followed quality standards and style guidelines while revising content through multiple stakeholder feedback cycles. Synthesized and structured information to make complex concepts understandable for diverse audiences.•Maintained logical structure and clarity in explanatory educational materials.•Performed rigorous fact-checking and grammar/consistency quality assurance.•Collaborated with editors and stakeholders across revision cycles.•Translated complex concepts into audience-appropriate learning content.

2021 - Present

AI Model Evaluator & Prompt Engineer — Arena AI (LLM Arena)

OtherTextText Generation

Evaluated and refined AI prompts and large language model outputs by systematically testing multiple models for quality and reliability. Analyzed accuracy, feature/limitation behavior, and output consistency to identify where models succeed or fail under different contexts. Documented hallucination patterns and assessed mitigation strategies to support safer and more dependable responses.•Designed targeted prompts to probe reasoning quality, output clarity, and consistency.•Used Arena AI comparative testing workflows to run structured evaluations across models.•Interpreted behavioral differences across AI systems to determine strengths and weaknesses.•Captured and reported hallucination patterns and notes on potential mitigation approaches.

2021 - 2026

Education

Work History