Ruks Ruks

Key Skills

Software

Label Studio

Other

Roboflow

CVAT

Top Subject Matter

AI-generated text

LLM prompt responses

Programming code

Top Data Types

Text

Image

Document

Top Task Types

Text Summarization

Question Answering

Computer Programming Coding

Text Generation

Data Collection

Prompt Response Writing SFT

Freelancer Overview

I am a Computer Science graduate with hands-on experience evaluating and rating AI-generated outputs across creative, technical, and instructional tasks. Through self-directed practice, I have developed a consistent methodology for assessing prompt-response quality, scoring outputs on accuracy, coherence, instruction-following, helpfulness, and safety. I am familiar with the kinds of failure modes that matter most in training data: hallucinations, sycophantic responses, instruction drift, and tone misalignment. My technical background in JavaScript and Python also means I can accurately evaluate and annotate code-related outputs that require domain knowledge beyond general literacy. What sets me apart is the combination of technical depth and creative sensitivity I bring to every labeling task. As a developer who has built interactive browser-based applications and a writer who regularly evaluates text for quality and clarity, I naturally apply both lenses when reviewing AI outputs, catching issues that purely technical or purely linguistic reviewers might miss. I treat every label as a real data point that influences model behavior, and I approach annotation work with the consistency, attention to detail, and accountability that production-grade AI training datasets demand.

Labeling Experience

AI Prompt Evaluator & Response Rater

Label StudioText

As an AI Prompt Evaluator & Response Rater, I systematically evaluated LLM prompt outputs for quality and instruction-following. I developed detailed annotation guides for measuring accuracy, coherence, helpfulness, and safety on a 1–5 scale. This work involved tracking and analyzing prompt-response pairs to identify recurring model issues. • Performed comprehensive rubrics-based evaluation of AI outputs • Identified hallucinations, instruction drift, and sycophantic model behaviors • Developed and refined annotation guidelines for prompt-rating tasks • Maintained detailed logs of evaluation data for RLHF purposes

As an AI Prompt Evaluator & Response Rater, I systematically evaluated LLM prompt outputs for quality and instruction-following. I developed detailed annotation guides for measuring accuracy, coherence, helpfulness, and safety on a 1–5 scale. This work involved tracking and analyzing prompt-response pairs to identify recurring model issues. • Performed comprehensive rubrics-based evaluation of AI outputs • Identified hallucinations, instruction drift, and sycophantic model behaviors • Developed and refined annotation guidelines for prompt-rating tasks • Maintained detailed logs of evaluation data for RLHF purposes

2024 - Present

Creative Writer & Text Quality Reviewer

Label StudioText

As a Creative Writer & Text Quality Reviewer, I produced and annotated written content for linguistic and quality attributes. I evaluated AI-generated and original texts for fluency, tone, grammar, and alignment with tasks. These activities utilized the same criteria as text annotation for AI datasets. • Assessed sentence, paragraph, and document-level consistency • Labeled text for grammar, tone, and appropriateness • Reviewed alignment of generated outputs with instructions • Provided feedback on text coherence and correctness

As a Creative Writer & Text Quality Reviewer, I produced and annotated written content for linguistic and quality attributes. I evaluated AI-generated and original texts for fluency, tone, grammar, and alignment with tasks. These activities utilized the same criteria as text annotation for AI datasets. • Assessed sentence, paragraph, and document-level consistency • Labeled text for grammar, tone, and appropriateness • Reviewed alignment of generated outputs with instructions • Provided feedback on text coherence and correctness

2021 - Present

Technical Content Creator & Code Reviewer

Other

As a Technical Content Creator & Code Reviewer, I reviewed and annotated code for correctness, logic, and stylistic compliance. I edited AI-generated code suggestions for compatibility and adherence to project standards. I also documented code using structured guidelines to ensure clarity and completeness. • Evaluated JavaScript and Python code for defects and efficiency • Improved AI-generated code samples through direct labeling and review • Labeled technical documentation for accuracy and completeness • Applied consistent annotation standards across multiple projects

As a Technical Content Creator & Code Reviewer, I reviewed and annotated code for correctness, logic, and stylistic compliance. I edited AI-generated code suggestions for compatibility and adherence to project standards. I also documented code using structured guidelines to ensure clarity and completeness. • Evaluated JavaScript and Python code for defects and efficiency • Improved AI-generated code samples through direct labeling and review • Labeled technical documentation for accuracy and completeness • Applied consistent annotation standards across multiple projects

2026 - 2026

Education

Work History