Herbey H.

Key Skills

Software

Don't disclose

Other

Top Subject Matter

AI/ML model training and evaluation

software engineering and technical QA

Frontend web development quality evaluation for AI output checking

Top Data Types

Text

Document

Top Task Types

RLHF

Freelancer Overview

AI Trainer & Quality Analyst (AI training and evaluation responsibilities), POLAR PL | ICT Manager / Software Engineer. Brings 8+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose and Other. Education includes Bachelor of Engineering, Abubakar Tafawa Balewa University (ATBU). AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including RLHF, Evaluation, and Rating.

Labeling Experience

AI Trainer & Quality Analyst (AI training and evaluation responsibilities), POLAR PL | ICT Manager / Software Engineer

Don't discloseTextRLHF

Performed AI training data annotation and quality evaluation across text-based instruction following and classification tasks. Conducted RLHF-style preference feedback, SFT data creation, and prompt-response assessments using rubrics and targeted error detection. Evaluated responses for factual accuracy, reasoning quality, and coding correctness to produce consistent training signals. • Text classification and instruction-following labeling • RLHF feedback and preference ranking • SFT/prompt engineering data preparation • Evaluation/Rating with rubric scoring

2022 - Present

Full Stack Developer (AI output evaluation context), NIA

Other

Developed full-stack applications with React.js and Node.js to support domain-grounded evaluation of AI outputs in web development scenarios. Used integration knowledge to assess correctness, expected behaviors, and technical constraints when reviewing generated content. Ensured practical engineering context for quality-oriented review and feedback loops. • Full-stack web implementation context • Assessment of integration/behavior correctness • Technical constraints validation • Engineering-grounded quality review

2022 - 2022

Full Stack Developer (evaluation-focused), NPK

Other

Reviewed and debugged application and database logic with an error-detection workflow relevant to evaluating AI-generated programming outputs. Developed relational and non-relational database solutions to broaden technical context for judging query and schema correctness. Applied systematic verification to ensure accuracy and best practices in evaluated outputs. • Code review and debugging for correctness • Database query/schema evaluation context • Structured error detection workflow • ORM and data modeling quality checks

2022 - 2022

Frontend Developer (used for AI output evaluation/quality checking), POStatus

Other

Reviewed and validated front-end implementation outputs using HTML, CSS, and JavaScript correctness criteria. Applied regulatory and UX compliance standards to judge quality and safety-relevant aspects of generated UI behavior. Ensured consistent evaluation comparable to response quality assessment and rubric-based scoring. • Cross-browser UI code review • UX/regulatory compliance checks • Quality scoring of front-end outputs • Structured debugging and validation approach

2022 - 2022

Education

Work History