Yomi A.

Key Skills

Software

Mercor

Top Subject Matter

Large language model (LLM) output evaluation and alignment

AI adoption evaluation research in public sector (dataset preparation and analysis)

Legal Services & Contract Review

Top Data Types

Text

Document

Top Task Types

Data Collection

Freelancer Overview

AI Generalist Contractor at Mercor Corporation (LLM prompt testing, response evaluation, ranking, and gold-standard targ. Brings 15+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Mercor. Education includes Doctor of Philosophy, University of Regina (2020) and Master of Science, Linnaeus University. AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Data Collection.

Labeling Experience

AI Generalist Contractor - Mercor Corporation

Text

Testing and refining complex prompts to improve large language model generation, reasoning quality, and factual accuracy. Evaluating and rating AI outputs across diverse domains to ensure compliance with project rubrics, style guides, and safety protocols. Providing quality human feedback by ranking responses and drafting gold-standard targets for model alignment, tone, and logical consistency. • Developed and refined prompt strategies for LLM performance • Performed rubric-based evaluation, annotation, and output quality checks • Wrote gold-standard responses to guide model training • Collaborated with multidisciplinary AI training teams

2026 - Present

AI Generalist Contractor at Mercor Corporation (LLM prompt testing, response evaluation, ranking, and gold-standard target response writing)

MercorText

Provided human evaluation and quality feedback on AI-generated outputs using project-specific rubrics and safety protocols. Ranked model responses and authored gold-standard target responses to guide alignment, tone, and logical consistency during training. Annotated and rated outputs across diverse domains to improve generation capability, reasoning, and factual accuracy of LLMs. • Tested and refined prompts to drive better model behavior • Performed evaluation, rating, and annotation of AI responses • Wrote gold-standard reference responses for training • Ensured outputs adhered to style guides, rubrics, and safety requirements

2026 - Present

PhD Researcher - Adoption of Artificial Intelligence at University of Regina (dataset collection/cleaning and evaluation methodology work)

TextData Collection

Led research focused on evaluating AI adoption in the public sector using large-scale datasets. Collected, cleaned, and analyzed datasets related to AI deployment to support assessment of performance and ethical alignment. Investigated user adoption patterns, trust vectors, and friction points to inform evaluation methodologies. • Developed methodologies for evaluating AI performance and ethical alignment • Collected and cleaned large-scale public-sector AI datasets • Analyzed socio-technical impacts and user trust factors • Studied adoption patterns and friction points

2020 - Present

Education

Work History