Open to opportunities

Mark Nderitu

@marknderitu

Message

I evaluate AI outputs and research evidence to deliver rigorous, defensible quality judgments.

United States

Message

What I'm looking for

I'm looking for self-directed AI research, evaluation, or content-quality work where I can apply rigorous evidence-based judgment, clear written critique, and consistent standards to complex or ambiguous material.

I've evaluated more than 5,000 written responses and research outputs, producing over 3,000 structured rationales on factual, logical, stylistic, and evidentiary issues. At NorthStar AI Research Group, I review AI-generated responses across business, technology, education, science, humanities, public policy, and general knowledge.

Previously at Deloitte Consulting and Pew Research Center, I turned qualitative and quantitative research into decision-ready briefs, assessed sources and methodologies, and strengthened analytical deliverables through rigorous editorial review. I focus on unsupported claims, missing context, contradictions, misleading framing, and gaps between evidence and conclusions.

I've also completed more than 1,000 fact-checking and source-verification assignments, developed cross-domain evaluation frameworks, and mentored more than 40 analysts and reviewers in critical reading and structured evaluation methods.

Experience

Work history, roles, and key accomplishments

Current

AI Evaluator & Research Analyst

Current

NorthStar AI Research Group

Oct 2023 - Present (2 years 10 months)

Review AI-generated responses across diverse domains, judging factual correctness, relevance, completeness, clarity, and reasoning quality. Produce structured written assessments identifying strengths, weaknesses, gaps, and logical flaws, while applying rubrics and independent judgment.

AI Evaluation Critical Reading Written Communication Quality Assurance Research Fact Checking Rubric Independent Judgment