Looking for a job

Sodiq Ajibade

@sodiqajibade

AI Model Evaluator on remote AI projects, scoring 10,000+ model responses and improving reviewer consistency with reusable checklists.

Nigeria

Message

On independent remote AI evaluation projects, I scored more than 10,000 model responses across finance, reasoning, coding and general knowledge. I ranked LLM responses for RLHF, identified hallucinations and reasoning errors, and created reusable checklists that cut turnaround time by about 25%.

At Annotasks and Atlas Capture, I annotated and validated more than 250,000 records for machine learning datasets, maintaining 99% annotation accuracy. I also used Python and Excel to analyze evaluation trends, and hold certifications in Google Data Analytics, IBM Data Science and Microsoft Azure AI Fundamentals.

Experience

Work history, roles, and key accomplishments

Current

Generalist

Current

Mercor and micro1

Jan 2024 - Present (2 years 10 months)

Reviewed and graded AI model outputs across many subject areas, flagging errors, hallucinations, and instruction-following failures. Annotated and evaluated text, image, video, and interface content, and rewrote AI-generated captions for accuracy and clarity.

AI Evaluation Data Annotation Content Review Quality Assurance Rubric Application

Current

Senior Data Annotation Specialist

Current

Annotasks and Atlas Capture

Jan 2023 - Present (3 years 10 months)

Annotated and validated over 250,000 text, image, and document records for machine learning training datasets. Ran quality audits, held 99% annotation accuracy, and carried out AI training tasks such as prompt evaluation and preference ranking.

Data Annotation Data Validation Quality Audits RLHF Prompt Evaluation Model Output Validation

Current

AI Model Evaluator and Generative AI Quality Analyst

Current

Independent Contractor

Jan 2023 - Present (3 years 10 months)

Completed over 10,000 evaluation tasks across finance, reasoning, coding, and general knowledge, scoring model answers against quality rubrics. Ranked and labeled LLM responses for RLHF, compared outputs side by side, and built reusable evaluation templates that cut turnaround time by about 25%.

LLM Evaluation RLHF Prompt Testing Data Annotation Python Excel Quality Assurance Error Analysis

AI Data Quality Analyst

Unknown

Jan 2023 - Dec 2023 (11 months)

Validated large AI training datasets and identified annotation errors affecting model performance. Produced quality reports showing data trends and inconsistencies, and supported machine learning pipeline improvements.

Data Quality Data Validation Error Analysis Quality Reporting Machine Learning

Legal Document Review Specialist

Unknown

Jan 2020 - Dec 2021 (1 year 11 months)

Checked confidential legal records for accuracy and compliance, and extracted structured information. Spotted inconsistencies and maintained detailed audit records and quality reports.

Document Review Data Extraction Quality Assurance Compliance Audit