Gbade L.

Key Skills

Software

Label Studio

Argilla

CVAT

Labelbox

Doccano

Top Subject Matter

AI-generated text

Prompt Engineering

AI Safety

Top Data Types

Text

Computer Code Programming

Document

Top Task Types

Question Answering

Text Summarization

RLHF

Red Teaming

Text Generation

Transcription

Fine-tuning

Computer Programming/Coding

Object Detection

Evaluation/Rating

Classification

Freelancer Overview

AI Evaluation & Prompt Engineering Specialist. Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include N and A. Education includes Certificate, IBM (2024). AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including Evaluation and Rating.

Labeling Experience

Programming & Technical Development (AI Code Annotation & Evaluation)

I reviewed code outputs for logical errors, edge cases, and output correctness within AI code generation evaluation workflows. My technical skills in Python, JavaScript, SQL, and Bash enabled me to participate in debugging annotation and function-calling review tasks. I employed professional version control and technical documentation practices to support consistent annotation standards. • Evaluated and debugged AI-generated programming code for correctness and logic. • Conducted function-calling reviews and code annotation on AI training platforms. • Used version tracking (GitHub) to document and maintain annotation work. • Ensured code evaluation adhered to quality and compliance rubrics.

2023 - Present

AI Evaluation & Prompt Engineering Specialist

Text

As an AI Evaluation & Prompt Engineering Specialist, I conducted structured annotation and evaluation of AI-generated text outputs against detailed rubrics. I performed RLHF-style preference ranking, adversarial prompt testing, and output refinement through prompt engineering. My responsibilities included identifying unsafe, biased, or policy-violating outputs and ensuring consistent label quality in line with industry best practices. • Evaluated over 200 AI-generated outputs for rubric accuracy, logical consistency, and instruction compliance. • Applied adversarial prompting techniques to test boundaries and detect model vulnerabilities. • Practiced and improved RLHF annotation workflows including preference ranking and HHH criteria. • Flagged outputs for safety issues, bias, and policy violations to mirror real QA processes.

2023 - Present

Education

Work History