For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
C
Confidence Oju

Confidence Oju

AI Evaluation Specialist | Multimodal Data Annotator

Nigeria flagCalabar, Nigeria
$20.00/hrIntermediateOther

Key Skills

Software

Other

Top Subject Matter

Artificial Intelligence / Machine Learning
Healthcare / Life Sciences
Technology / Software

Top Data Types

TextText
ImageImage
AudioAudio

Top Task Types

Evaluation/RatingEvaluation/Rating
RLHFRLHF
Text GenerationText Generation
Question AnsweringQuestion Answering
Object DetectionObject Detection

Freelancer Overview

AI Training Tasker | Outlier.ai. Brings 9+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Master of Science, University of Calabar (2024) and Bachelor of Science, Cross River University of Technology (2019). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Classification. I am an experienced AI training data specialist with over 1 year of active task completion on Outlier, having contributed to more than nine distinct data labeling and model evaluation projects. My work spans multimodal AI evaluation, conversational response assessment, text-to-image fidelity rating, speech-to-speech quality analysis, and video generation evaluation, covering a broad spectrum of modalities including text, image, audio, and video. I bring a rigorous, quality-focused approach to every task, informed by my academic background in Biochemistry and Chemical Pathology, which has trained me in precise observation, systematic analysis, and evidence-based judgment. In addition to my AI training experience, I hold a Master of Science from the University of Calabar (2024) and a Bachelor of Science from Cross River University of Technology (2019), both attained with top academic distinction. My scientific training has sharpened my ability to evaluate complex outputs with attention to detail, consistency, and structured reasoning skills that translate directly into high-quality data labeling, RLHF annotation, and model evaluation work. I am committed to contributing accurate, well-reasoned annotations that meaningfully support the development of safe and capable AI systems.

IntermediateEnglishIgbo

Labeling Experience

Multimodal Multi-Turn Dialogue Evaluation (Omni Multi-Turn ELO)

ImageEvaluation Rating
Evaluated multimodal AI systems across extended multi-turn dialogue interactions, rating model performance on context retention, response coherence, cross-modal consistency, and overall conversational quality. Applied ELO comparative ratings to rank model outputs and identify performance patterns across turns. This task demanded strong analytical skills and the ability to track context across complex, multi-step interactions.

Evaluated multimodal AI systems across extended multi-turn dialogue interactions, rating model performance on context retention, response coherence, cross-modal consistency, and overall conversational quality. Applied ELO comparative ratings to rank model outputs and identify performance patterns across turns. This task demanded strong analytical skills and the ability to track context across complex, multi-step interactions.

2025 - Present

Speech-to-Speech Model Quality Evaluation (S2S ELO)

AudioEvaluation Rating
Assessed speech-to-speech AI model outputs by evaluating audio responses for naturalness, clarity, prosody, response accuracy, and speaker consistency. Conducted comparative ELO-style evaluations across multiple model outputs to identify higher-quality speech generation. This project required attentive listening skills and the ability to apply consistent quality criteria to nuanced audio characteristics.

Assessed speech-to-speech AI model outputs by evaluating audio responses for naturalness, clarity, prosody, response accuracy, and speaker consistency. Conducted comparative ELO-style evaluations across multiple model outputs to identify higher-quality speech generation. This project required attentive listening skills and the ability to apply consistent quality criteria to nuanced audio characteristics.

2025 - Present

Text-to-Video Model Evaluation (Omni T2V ELO)

VideoEvaluation Rating
Evaluated AI-generated video outputs against text prompts, assessing each video for prompt adherence, temporal consistency, visual quality, motion naturalness, and overall coherence. Applied ELO-style comparative rating to rank model outputs and support iterative model improvement. This task required both technical and aesthetic judgment in evaluating dynamic visual content across multiple generative models.

Evaluated AI-generated video outputs against text prompts, assessing each video for prompt adherence, temporal consistency, visual quality, motion naturalness, and overall coherence. Applied ELO-style comparative rating to rank model outputs and support iterative model improvement. This task required both technical and aesthetic judgment in evaluating dynamic visual content across multiple generative models.

2025 - Present

Text-to-Image Prompt Fidelity Evaluation

TextEvaluation Rating
Evaluated AI-generated images against corresponding text prompts, rating each output for prompt alignment, visual quality, compositional accuracy, and aesthetic fidelity. Compared multiple model outputs side-by-side to identify which generations best represented the intended prompt. This task demanded high visual literacy and precise interpretation of both textual descriptions and image content.

Evaluated AI-generated images against corresponding text prompts, rating each output for prompt alignment, visual quality, compositional accuracy, and aesthetic fidelity. Compared multiple model outputs side-by-side to identify which generations best represented the intended prompt. This task demanded high visual literacy and precise interpretation of both textual descriptions and image content.

2025 - Present

Multi-Turn Conversational Image Annotation (Furniture Removal)

ImageEvaluation Rating
Annotated and evaluated multi-turn conversational interactions involving image-based furniture removal tasks. Assessed the AI model's ability to follow sequential instructions across dialogue turns, rating output quality based on instruction adherence, visual accuracy, and contextual consistency. This project required careful attention to both visual content and conversational flow across extended interactions.

Annotated and evaluated multi-turn conversational interactions involving image-based furniture removal tasks. Assessed the AI model's ability to follow sequential instructions across dialogue turns, rating output quality based on instruction adherence, visual accuracy, and contextual consistency. This project required careful attention to both visual content and conversational flow across extended interactions.

2025 - Present

Education

U

University of Calabar

Master of Science, Chemical Pathology (Clinical Chemistry and Immunology)

Master of Science
2022 - 2024
C

Cross River University of Technology

Bachelor of Science, Biochemistry

Bachelor of Science
2015 - 2019

Work History

W

Wealthy Wanderers FC

Team Captain

Calabar
2023 - Present
U

University Of Calabar

Graduate Teaching Assistant

Calabar
2023 - Present