For employers

Hire this AI Trainer

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

Invite to Job
I
Ikenna A.

Ikenna A.

AI Evaluator & RLHF Specialist | Domain Expert (Legal & Writing)

Canada flagToronto, Canada

Key Skills

Software

Scale AIScale AI
MercorMercor

Top Subject Matter

AI model training and evaluation for tone
Accuracy Domain Expertise
Context Domain Expertise

Top Data Types

TextText
DocumentDocument

Top Task Types

RLHFRLHF

Freelancer Overview

AI Trainer | Outlier / Scale AI (Remote). Brings 14+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Scale AI and Mercor. Education includes Bachelor of Arts, Carleton University. AI-training focus includes data types such as Text and labeling workflows including RLHF, Evaluation, and Rating.

Labeling Experience

Mercor

AI Evaluator & Writer | Mercor (Remote)

MercorMercorTextText

Audited long-form analytical responses and synthetic text generated by large language models for contextual truthfulness and readability. Designed detailed benchmarking prompts to test domain-specific limitations under complex creative and professional constraints. Supplied granular structured feedback and rewrite variants to optimize model execution parameters and tone tracking. • Evaluated LLM outputs for truthfulness, formatting, and target readability • Built benchmarking prompt suites to measure model limitations across constraints • Produced structured feedback and alternative rewrites to guide improvements • Tuned guidance toward better tone tracking and execution parameters

2025 - 2025
Scale AI

AI Trainer | Outlier / Scale AI (Remote)

Scale AIScale AITextTextRLHFRLHF

Prepared and structured written content (including text prompts and feedback) to train AI models on tone, accuracy, and contextual correctness. Applied Reinforcement Learning from Human Feedback (RLHF) concepts to improve model efficiency and alignment. Performed quality assurance review of written outputs to ensure clarity and consistency. • Curated training materials to reinforce model understanding of tone and context • Supported RLHF-related iteration using human feedback on outputs • Ensured outputs met legal and ethical requirements including safety and harmlessness • Reviewed and provided QA on other analysts’ written work for readability

2024 - 2025

Education

C

Carleton University

Bachelor of Arts, Law

Bachelor of Arts
Not specified

Work History

S

Self-Employed

Freelance Writer and Editor

Toronto
2024 - Present
T

Two Talent School

Curriculum Developer and ESL Instructor

Toronto
2017 - 2024