For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
Lucky Umoru Zakari

Lucky Umoru Zakari

AI Transformation Specialist, Integra8AI

Nigeria flagLagos, Nigeria
$10.00/hrIntermediateAppenLabelboxSuperannotate

Key Skills

Software

AppenAppen
LabelboxLabelbox
SuperAnnotateSuperAnnotate
RoboflowRoboflow

Top Subject Matter

AI system evaluation and workflow optimization
Healthcare AI
medical report evaluation

Top Data Types

TextText
VideoVideo
AudioAudio
DocumentDocument

Top Task Types

Classification
Object Detection

Freelancer Overview

AI Transformation Specialist, Integra8AI. Brings 4+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Arts, University of Benin (2014). AI-training focus includes data types such as Text and Video and labeling workflows including Evaluation and Rating.

IntermediateEnglish

Labeling Experience

AI Compliance Evaluator – DeFi Compass Agent

Text
With Regulatory DeFi Compass Agent, I assessed AI-generated outputs for DeFi compliance analyses, rating risk scores and regulatory overlays on yield data. My work involved synthesizing financial, legal, and regulatory details, checking for factual accuracy, clarity, and nuanced quality. This experience required domain expertise and precise rubric-based evaluation of textual risk assessments. • Evaluated DeFi AI outputs for regulatory accuracy • Used rubrics to assess clarity and usefulness in financial contexts • Synthesized information from multiple legal and financial sources • Reported findings to inform model improvements

With Regulatory DeFi Compass Agent, I assessed AI-generated outputs for DeFi compliance analyses, rating risk scores and regulatory overlays on yield data. My work involved synthesizing financial, legal, and regulatory details, checking for factual accuracy, clarity, and nuanced quality. This experience required domain expertise and precise rubric-based evaluation of textual risk assessments. • Evaluated DeFi AI outputs for regulatory accuracy • Used rubrics to assess clarity and usefulness in financial contexts • Synthesized information from multiple legal and financial sources • Reported findings to inform model improvements

2023 - Present

Quality Evaluator – StreamScribe-AI

Video
In the StreamScribe-AI initiative, I conducted quality ratings and assessments of AI-processed livestream highlights, summaries, and content clips. The work required precise judgment of relevance, effectiveness, and content quality, ensuring outputs met strict project guidelines for video analytics. My evaluations informed the improvement of both AI summary generation and highlight detection algorithms. • Rated quality and relevance of AI-generated video clips • Ensured effectiveness of summary and highlight extraction • Used rubric-based scoring for consistency • Provided feedback for prompt and model revisions

In the StreamScribe-AI initiative, I conducted quality ratings and assessments of AI-processed livestream highlights, summaries, and content clips. The work required precise judgment of relevance, effectiveness, and content quality, ensuring outputs met strict project guidelines for video analytics. My evaluations informed the improvement of both AI summary generation and highlight detection algorithms. • Rated quality and relevance of AI-generated video clips • Ensured effectiveness of summary and highlight extraction • Used rubric-based scoring for consistency • Provided feedback for prompt and model revisions

2023 - Present

Evaluator – SympSense-AI

Text
For the SympSense-AI project, I evaluated multi-modal healthcare AI outputs involving text, medical reports, and clinical documents for factuality and clinical relevance. My work focused on reviewing generated outputs for accuracy and utility in a healthcare setting, applying clear guidelines for consistent assessments. The process included detailed checks for completeness and consistency with medical standards. • Reviewed AI outputs for factual and clinical correctness • Applied guidelines for healthcare document analysis • Assessed completeness and usability for clinicians and patients • Documented evaluation findings to iterate on model prompts

For the SympSense-AI project, I evaluated multi-modal healthcare AI outputs involving text, medical reports, and clinical documents for factuality and clinical relevance. My work focused on reviewing generated outputs for accuracy and utility in a healthcare setting, applying clear guidelines for consistent assessments. The process included detailed checks for completeness and consistency with medical standards. • Reviewed AI outputs for factual and clinical correctness • Applied guidelines for healthcare document analysis • Assessed completeness and usability for clinicians and patients • Documented evaluation findings to iterate on model prompts

2023 - Present

AI Transformation Specialist, Integra8AI

Text
As the AI Transformation Specialist at Integra8AI, I evaluated AI system outputs for accuracy, clarity, and completeness in real-world contexts. Responsibilities included side-by-side model comparisons, prompt engineering, and rubric development to assess the performance of language models and agents. I executed asynchronous, domain-specific research tasks to inform guidelines and identify model failure modes. • Designed and refined evaluation rubrics for factuality and helpfulness • Analyzed LLM/agent outputs and delivered prompt and rubric iterations • Wrote technical content and client deliverables on evaluation best practices • Managed asynchronous quality assessment workflow in a remote setting

As the AI Transformation Specialist at Integra8AI, I evaluated AI system outputs for accuracy, clarity, and completeness in real-world contexts. Responsibilities included side-by-side model comparisons, prompt engineering, and rubric development to assess the performance of language models and agents. I executed asynchronous, domain-specific research tasks to inform guidelines and identify model failure modes. • Designed and refined evaluation rubrics for factuality and helpfulness • Analyzed LLM/agent outputs and delivered prompt and rubric iterations • Wrote technical content and client deliverables on evaluation best practices • Managed asynchronous quality assessment workflow in a remote setting

2023 - Present

Education

U

University of Benin

Bachelor of Arts, International Studies and Diplomacy

Bachelor of Arts
2010 - 2014

Work History

I

Integra8AI

Founder & AI Transformation Specialist

Lagos
2023 - Present