For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
E
Emirhan D.

Emirhan D.

LLM Evaluator | RLHF, SFT, Red Teaming & Code Review

Turkey flagAnkara, Turkey

Key Skills

Software

Scale AIScale AI
LabelboxLabelbox
Data Annotation TechData Annotation Tech
CVATCVAT
RemotasksRemotasks
MindriftMindrift
OneFormaOneForma
AppenAppen
Surge AISurge AI
TolokaToloka
TelusTelus

Top Subject Matter

Artificial Intelligence (AI) & Machine Learning
Software Development
Information Technology

Top Data Types

TextText
Computer Code ProgrammingComputer Code Programming
DocumentDocument

Top Task Types

Text GenerationText Generation
Question AnsweringQuestion Answering
Text SummarizationText Summarization
RLHFRLHF
Fine-tuningFine-tuning
Red TeamingRed Teaming
Evaluation/RatingEvaluation/Rating
Computer Programming/CodingComputer Programming/Coding
Function CallingFunction Calling
Prompt + Response Writing (SFT)Prompt + Response Writing (SFT)

Freelancer Overview

I am an LLM Evaluator specializing in RLHF, SFT, red teaming, prompt-response writing, function calling, and code review tasks. I evaluate AI-generated responses for accuracy, reasoning quality, instruction-following, safety, factual consistency, formatting, tone, usefulness, and code correctness. I am comfortable working with detailed guidelines, rubrics, rating systems, and quality-focused annotation workflows. My goal is to provide consistent, reliable, and well-reasoned evaluations that help improve AI model performance.

Labeling Experience

AI Response Evaluator & RLHF Specialist

TextTextRLHFRLHF

Evaluated LLM-generated responses based on accuracy, relevance, clarity, tone, and factual consistency using RLHF principles. Performed detailed content quality reviews and data annotation across dual-language workflows. Compared multiple AI outputs to select the most helpful, complete, and reliable responses while meticulously identifying logical inconsistencies, factual errors, and strict guideline violations. Provided structured, objective feedback to improve model alignment and instruction-following capabilities.

2025 - Present

LLM Code Evaluator & Technical Rater

Computer Code ProgrammingComputer Code ProgrammingComputer Programming/CodingComputer Programming/Coding

Evaluated, debugged, and rated AI-generated code snippets with a strong focus on backend services, server-side logic, and database management. Assessed code for logical accuracy, syntax correctness, efficiency, and potential security vulnerabilities. Conducted rigorous testing of AI responses to ensure they meet standard software development principles and provided structured technical feedback to improve the model's coding accuracy.

2026 - Present

Education

A

Anadolu University

Associate Degree, Backend Software Development

Associate Degree
2024 - 2026

Work History

I

Independent Freelancer

Backend Software Developer (Freelance)

Ankara
2023 - Present