Open to opportunities

Theuri Benjamin

@theuribenjamin

Message

I evaluate, rank, and improve AI-generated content for reliable LLM training.

Kenya

Message

What I'm looking for

I'm looking for remote, project-based AI evaluation or annotation work where I can apply structured guidelines, assess model outputs, support LLM training, and deliver accurate, high-quality work independently.

I've evaluated and improved AI-generated content for Outlier AI, TELUS Digital, RWS, and Sama, rating outputs, writing prompts, ranking responses, and applying structured guidelines across generative AI training projects. My work supports LLM training, fine-tuning, and RLHF through accurate assessment of quality, relevance, accuracy, and appropriateness.

I also bring experience as a freelance writer and content researcher, where I fact-checked, summarized, paraphrased, and edited content under strict quality standards. I work independently in remote, deadline-driven environments and combine strong written English with careful annotation, research, and quality assurance.

Experience

Work history, roles, and key accomplishments

AI Rater, Personalized Internet Assessor

TELUS Digital

Jan 2024 - Dec 2025 (1 year 11 months)

Scored content relevancy on 1-5 scales and reviewed search and model outputs for performance. Ranked AI-generated responses to support RLHF initiatives.

Search Evaluation

AI Trainer, AI Evaluator

Outlier AI

Jan 2024 - Dec 2025 (1 year 11 months)

Rated and assessed AI model outputs against detailed evaluative rubrics, scoring response quality, accuracy, and appropriateness. Wrote original prompts and rewrote AI-generated text to improve clarity and guideline compliance.

AI model evaluation Prompt Generation Prompt Engineering Quality Assurance

AI Data Annotator, AI Evaluator

RWS

Jan 2024 - Dec 2025 (1 year 11 months)

Labeled and categorized content elements for model training and produced concise summaries of source text. Applied structured annotation guidelines consistently across high-volume datasets.

Data Annotation Quality Assurance

AI Evaluator

Sama

Oct 2024 - Nov 2024 (1 month)

Evaluated AI-generated responses for accuracy, relevance, and guideline adherence. Delivered guideline-compliant assessments under tight deadlines.

AI model evaluation Quality Assurance

Freelance Writer & Content Researcher

Self Employed

Jan 2021 - Feb 2024 (3 years 1 month)

Researched, drafted, and edited long- and short-form written content across varied subject areas. Fact-checked source material and summarized complex information for general audiences.

Writing Editing Research Fact Checking Summarization

Customer Service Representative

Postal Corporation of Kenya

Mar 2023 - Oct 2023 (7 months)

Communicated with customers through inbound and outbound calls and email to address inquiries and resolve issues. Documented interactions and applied coaching feedback to improve service quality.

Customer Service Active Listening Problem Solving Documentation