For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
Osayuki “yuki” Aganmwonyi

Osayuki “yuki” Aganmwonyi

AI Product Manager | Multi-Agent Systems | LLM Evaluation & Prompt Engineering | LLM Reasoning & Quality Reviewer | Technical Writer

NIGERIA flag
Lagos, Nigeria
$20.00/hrExpert

Key Skills

Software

No software listed

Top Subject Matter

Conversational AI
LLM
Multi-agent systems

Top Data Types

TextText
DocumentDocument
ImageImage

Top Task Types

Prompt Response Writing SFT

Freelancer Overview

AI Output Evaluation & LLM Reviewer (TreeKlUp/Xel Platform). Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Engineering with Honors, Delta State University (2017). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Prompt + Response Writing.

ExpertYorubaEnglish

Labeling Experience

AI Research & Evaluation Practitioner

Text
Collaborated with AI systems and large language models (LLMs) to analyze, review, and refine outputs for accuracy, clarity, and logical consistency across diverse technical and market research domains. Utilized prompt engineering, structured research, and multi-source verification to assess and improve AI-generated outputs. Applied evaluation frameworks and provided structured feedback for improving reasoning, factual correctness, and bias detection. • Reviewed outputs for logical soundness, factual grounding, and absence of reasoning errors. • Designed prompt templates and evaluation rubrics tailored to real-world scenario requirements. • Conducted web research and fact verification to support evidence-based assessment. • Delivered comprehensive written feedback, supporting iterative improvement of AI systems.

Collaborated with AI systems and large language models (LLMs) to analyze, review, and refine outputs for accuracy, clarity, and logical consistency across diverse technical and market research domains. Utilized prompt engineering, structured research, and multi-source verification to assess and improve AI-generated outputs. Applied evaluation frameworks and provided structured feedback for improving reasoning, factual correctness, and bias detection. • Reviewed outputs for logical soundness, factual grounding, and absence of reasoning errors. • Designed prompt templates and evaluation rubrics tailored to real-world scenario requirements. • Conducted web research and fact verification to support evidence-based assessment. • Delivered comprehensive written feedback, supporting iterative improvement of AI systems.

2024 - Present

Prompt Engineer — Multi-Agent AI System (TreeKlUp/Xel)

TextPrompt Response Writing SFT
Designed and refined prompt strategies and structured instructions to guide multi-agent AI systems toward higher quality, context-aware, and reliable conversational outputs. Created agent-specific prompts to optimize agent behavior for intent recognition, continuity, and user satisfaction. Regularly reviewed, adjusted, and iterated prompts as part of continuous system improvement processes. • Developed and tested prompt templates across Support, Product, Community, Campaign, and Help agent types. • Measured impact of prompt changes using structured qualitative and quantitative evaluation methods. • Ensured prompts reflected best practices in AI guidance, transparency, and user intent resolution. • Maintained documentation of prompt logic, language patterns, and outcome scenarios.

Designed and refined prompt strategies and structured instructions to guide multi-agent AI systems toward higher quality, context-aware, and reliable conversational outputs. Created agent-specific prompts to optimize agent behavior for intent recognition, continuity, and user satisfaction. Regularly reviewed, adjusted, and iterated prompts as part of continuous system improvement processes. • Developed and tested prompt templates across Support, Product, Community, Campaign, and Help agent types. • Measured impact of prompt changes using structured qualitative and quantitative evaluation methods. • Ensured prompts reflected best practices in AI guidance, transparency, and user intent resolution. • Maintained documentation of prompt logic, language patterns, and outcome scenarios.

2025 - 2026

AI Output Evaluation & LLM Reviewer (TreeKlUp/Xel Platform)

Text
Led structured evaluation and validation of large language model (LLM) outputs for the Xel multi-agent AI system implemented within the TreeKlUp WhatsApp chat commerce platform. Designed and executed assessment criteria to measure LLM performance in intent detection, conversation flow, and response accuracy for each specialized agent. Applied prompt engineering and AI eval frameworks to inform system reliability, accuracy, and user experience. • Reviewed and validated LLM outputs across six agentic modules for sequence flow correctness and factual grounding. • Developed rubrics matching business process logic, domain requirements, and AI output quality standards. • Collaborated directly with engineering and product teams to align AI module performance with acceptance thresholds. • Verified completeness, accuracy, and usability of generated responses before deployment.

Led structured evaluation and validation of large language model (LLM) outputs for the Xel multi-agent AI system implemented within the TreeKlUp WhatsApp chat commerce platform. Designed and executed assessment criteria to measure LLM performance in intent detection, conversation flow, and response accuracy for each specialized agent. Applied prompt engineering and AI eval frameworks to inform system reliability, accuracy, and user experience. • Reviewed and validated LLM outputs across six agentic modules for sequence flow correctness and factual grounding. • Developed rubrics matching business process logic, domain requirements, and AI output quality standards. • Collaborated directly with engineering and product teams to align AI module performance with acceptance thresholds. • Verified completeness, accuracy, and usability of generated responses before deployment.

2025 - 2026

LLM Output Evaluator — AI Advisory Platform (RAVEN)

Text
As Product Manager, evaluated LLM outputs for an AI-powered advisory platform designed for African farmers, ensuring domain-appropriate factual accuracy and relevance. Applied domain expertise and evaluation frameworks to measure LLM responses against agricultural requirements and use cases. Conducted structured assessments and provided detailed, actionable feedback on output quality and correctness. • Compared AI-generated responses with expert-validated agricultural information for accuracy. • Identified gaps, logical errors, or factual inaccuracies in model outputs and reported findings. • Collaborated with domain experts (ANA, CGIAR, IITA) to refine evaluation criteria. • Documented evaluation process, aligned outputs with user needs, and advised on future AI fine-tuning.

As Product Manager, evaluated LLM outputs for an AI-powered advisory platform designed for African farmers, ensuring domain-appropriate factual accuracy and relevance. Applied domain expertise and evaluation frameworks to measure LLM responses against agricultural requirements and use cases. Conducted structured assessments and provided detailed, actionable feedback on output quality and correctness. • Compared AI-generated responses with expert-validated agricultural information for accuracy. • Identified gaps, logical errors, or factual inaccuracies in model outputs and reported findings. • Collaborated with domain experts (ANA, CGIAR, IITA) to refine evaluation criteria. • Documented evaluation process, aligned outputs with user needs, and advised on future AI fine-tuning.

2022 - 2024

Education

D

Delta State University

Bachelor of Engineering with Honors, Mechanical Engineering

Bachelor of Engineering with Honors
2017 - 2017

Work History

F

FBIS Technologies

Lead Product Manager

Lagos
2025 - Present
F

FBIS Technologies

Product Implementation Lead

Lagos
2024 - 2025