Open to opportunities

Anthony Edet

@anthonyedet

AI Evaluation Specialist ensuring accurate, coherent, policy-aligned LLM outputs with high-volume, rubric-based review precision.

Nigeria

Message

What I'm looking for

I’m looking for an evaluation-focused role where I can apply rubric-based LLM review, RLHF pairwise feedback, and high-accuracy QA to improve content quality, alignment, and user trust—while working with structured guidelines and measurable targets.

I’m an AI Evaluation Specialist focused on content quality, accuracy, and policy alignment across large language model systems. I review AI-generated responses for coherence, cultural sensitivity, hallucinations, and factual inconsistencies, then deliver clear, actionable feedback that improves model performance.

In my current role, I evaluate 120–200+ AI-generated responses daily, using structured rubric-based frameworks to support RLHF training through pairwise comparisons and prompt rating. I consistently maintain 95%+ quality scores while meeting strict turnaround deadlines in a high-volume, deadline-driven environment.

My editorial and creative background strengthens how I assess narrative structure, tone consistency, and user experience—skills I’ve applied as a creative production manager and content operations reviewer. I also bring strong operational discipline from leading data operations with ~99% accuracy, alongside hands-on experience with dataset preparation, QA, spreadsheet analysis, and performance metric tracking using Excel and Google Sheets.

Experience

Work history, roles, and key accomplishments

Current

AI Response Evaluator

Current

Light House Tech Hub

Jun 2025 - Present (11 months)

Evaluates 120–200+ AI-generated responses daily for accuracy, clarity, coherence, and policy compliance using structured rubric reviews. Performs pairwise comparisons and prompt rating to support RLHF training, maintaining 95%+ quality scores under strict turnaround deadlines.

AI Response Evaluation RLHF Prompt Rating Pairwise Comparisons Hallucination Detection Fact Checking

Current

Storytelling Facilitator

Current

Rural Secondary Schools Program

Jan 2024 - Present (2 years 4 months)

Developed and delivered a curriculum on narrative structure and content evaluation, training 162 students using structured rubrics and quality tracking. Translated complex evaluation concepts into repeatable frameworks for learners with no prior media exposure.

Curriculum Development Workshop Facilitation

Current

Administrative Program Coordinator

Current

Community Based Development Partners Inc.

Mar 2023 - Present (3 years 2 months)

Reviewed and approved media outputs for clarity, accuracy, and audience suitability while maintaining consistent voice across platforms. Managed multi-platform content workflows aligned with editorial and communication standards.

Content Moderation Editorial Standards Audience Suitability Evaluation

Current

Creative Production Manager

Current

Citizens of Light Church Global

Jan 2023 - Present (3 years 4 months)

Evaluated scripts and visual narrative assets for quality, coherence, tone consistency, and cultural relevance. Reduced production turnaround time by 25% and increased team productivity by 60% through tighter workflow design and structured quality benchmarking.

Script Evaluation Content Quality Benchmarking Workflow Design Creative Production Cultural Sensitivity Review

AI Data Contributor

Appen

Jan 2023 - Jan 2025 (2 years)

Completed 100+ annotation tasks daily across multiple AI training projects, maintaining 95%+ accuracy in data labeling and evaluation. Conducted search relevance evaluation and content review, tracking performance metrics in Excel and Google Sheets.

Data Annotation Data Labeling Search Relevance Content Review Performance Metrics

Test Center Operations Lead

Metro Computer-Based Test Center

Feb 2020 - Jan 2023 (2 years 11 months)

Managed high-volume data operations with approximately 99% accuracy in error-sensitive, time-constrained environments. Improved operational accuracy by 20–25% through QA process optimization and team training, and performed large-scale data cleaning and integrity checks.

Data Cleaning Data Validation Performance Analysis Operational Accuracy Improvement