For employers

Hire this AI Trainer

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

Invite to Job
David Leroux

David Leroux

Software Developer | AI Model Evaluation & Training

FRANCE flag
Fayet le Chateau, France
$25.00/hrIntermediateInternal Proprietary Tooling

Key Skills

Software

Internal/Proprietary Tooling

Top Subject Matter

No subject matter listed

Top Data Types

Computer Code ProgrammingComputer Code Programming

Top Label Types

RLHF
Evaluation Rating
Computer Programming Coding
Prompt Response Writing SFT

Freelancer Overview

I am a detail-oriented application developer with strong analytical and technical skills, developed through hands-on experience in software development and technical support roles. My background includes modeling complex systems using UML, building ERP applications with Java Spring Boot and Angular, and adhering to best practices such as Agile/Scrum. I am adept at understanding client requirements, following precise processes, and ensuring high data quality—skills that translate well to data labeling and AI training data environments. My experience troubleshooting and documenting technical issues has given me a meticulous approach, and I am always eager to learn new tools and methods to contribute effectively to data annotation and machine learning projects.

IntermediateEnglishFrench

Labeling Experience

LLM Coding Evaluation & Python Data Labeling Specialist

Internal Proprietary ToolingComputer Code ProgrammingRLHFEvaluation Rating
Worked on LLM evaluation and human feedback projects focused on code generation and reasoning tasks (Python-heavy). Rated model-generated responses across multiple structured dimensions including Instruction Following, Truthfulness, Style & Clarity, Verbosity, and Overall Quality. Compared dual responses, assigned preference rankings, and wrote detailed justifications explaining reasoning and logical trade-offs. Ensured strict adherence to system prompts, user prompts, and conversation history context when evaluating outputs. Identified hallucinations, logical inconsistencies, instruction violations, and core-requirement failures in technical responses. Contributed to reinforcement learning from human feedback (RLHF) pipelines for improving code reliability and reasoning alignment.

Worked on LLM evaluation and human feedback projects focused on code generation and reasoning tasks (Python-heavy). Rated model-generated responses across multiple structured dimensions including Instruction Following, Truthfulness, Style & Clarity, Verbosity, and Overall Quality. Compared dual responses, assigned preference rankings, and wrote detailed justifications explaining reasoning and logical trade-offs. Ensured strict adherence to system prompts, user prompts, and conversation history context when evaluating outputs. Identified hallucinations, logical inconsistencies, instruction violations, and core-requirement failures in technical responses. Contributed to reinforcement learning from human feedback (RLHF) pipelines for improving code reliability and reasoning alignment.

2024 - 2025

Education

C

Concepteur Développeur D'Applications

Diploma Level 6, Application Development

Diploma Level 6
2023 - 2024
D

Développeur Web et Web Mobile

Diploma Level 5, Web and Mobile Web Development

Diploma Level 5
2022 - 2023

Work History

E

Edidebs

Application Developer Intern

Fayet le Chateau
2023 - 2024
C

Compagnie Du Sav

Home Appliance Service Technician

Fayet Le Chateau
2016 - 2021