For employers

Hire this AI Trainer

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

Invite to Job
N
Nafeh

Nafeh

RLHF Consultant

Canada flagToronto, Canada

Key Skills

Software

Internal/Proprietary Tooling
Scale AIScale AI
TelusTelus
LabelboxLabelbox

Top Subject Matter

Multimodal LLM evaluation for RLHF
image-to-text and video reasoning dataset review
Legal Services & Contract Review

Top Data Types

TextText
ImageImage
DocumentDocument

Top Task Types

RLHFRLHF
Bounding BoxBounding Box
PolygonPolygon
ClassificationClassification
Text GenerationText Generation
Question AnsweringQuestion Answering
Fine-tuningFine-tuning
TranscriptionTranscription
Evaluation/RatingEvaluation/Rating

Freelancer Overview

RLHF Consultant (AI Model Training) at Outlier, Scale AI (Part time Contract) and Mercor (Part-time Contract). Brings 14+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Education includes Bachelor of Science, Bangladesh University of Professionals (2014). AI-training focus includes data types such as Text and labeling workflows including RLHF.

Labeling Experience

RLHF Consultant (Generalist) at Mercor

DocumentDocumentEvaluation/RatingEvaluation/Rating

Evaluate and compare multiple powerpoint presentation, excel spreadsheet, word document, PDF generated for a prompt and given data by multimodal LLM on multiple aspects, starting from aesthetics, completeness, factual content and overall look & feel.

2026 - Present

RLHF Consultant (AI Training) at Outlier

VideoVideoRLHFRLHF

Served as an RLHF consultant and senior reviewer, evaluating multimodal LLM outputs for reasoning accuracy, safety alignment, and visual-spatial fidelity to support model fine-tuning. Audited complex training datasets for image-to-text and video-reasoning tasks, identifying issues that contribute to hallucinations and degraded response precision. Provided structured feedback to improve next-generation AI/ML integration programs and evaluation quality. • Assessed reasoning accuracy and safety alignment of multimodal LLM responses • Reviewed visual-spatial fidelity for image/video understanding • Audited image-to-text and video-reasoning datasets for label quality issues • Contributed feedback loops to reduce hallucinations and improve precision in edge cases

2025 - Present
Scale AI

RLHF Consultant (AI Model Training) at Outlier

Scale AIScale AIImageImageRLHFRLHF

Served as an RLHF consultant and senior reviewer, evaluating multimodal LLM outputs for reasoning accuracy, safety alignment, and visual-spatial fidelity to support model fine-tuning. Audited complex training datasets for image-to-text and video-reasoning tasks, identifying issues that contribute to hallucinations and degraded response precision. Provided structured feedback to improve next-generation AI/ML integration programs and evaluation quality. • Assessed reasoning accuracy and safety alignment of multimodal LLM responses • Reviewed visual-spatial fidelity for image/video understanding • Audited image-to-text and video-reasoning datasets for label quality issues • Contributed feedback loops to reduce hallucinations and improve precision in edge cases

2025 - Present

Education

B

Bangladesh University of Professionals

Bachelor of Science, Computer Science and Engineering

Bachelor of Science
2011 - 2014

Work History

R

Riseup Pro

Director of Engineering

Toronto
2025 - Present
A

Angi

Engineering Manager

Toronto
2022 - 2024