For employers

Hire this AI Trainer

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

Invite to Job
R

Rodrigo Silva De Oliveira

AI Data Trainer & RLHF Annotator | Freelance Contractor (AI Platforms)

Brazil flagJundiaí, Brazil
Intermediate

Key Skills

Software

No software listed

Top Subject Matter

AI Model Alignment
Portuguese-english Domain Expertise
Linguistic Evaluation

Top Data Types

TextText
DocumentDocument

Top Task Types

RLHF

Freelancer Overview

AI Data Trainer & RLHF Annotator | Freelance Contractor (AI Platforms). Brings 7+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Certificate of Advanced English Proficiency, EF SET (2024) and Certificate in Cybersecurity Compliance Framework, IBM (2024). AI-training focus includes data types such as Text and labeling workflows including RLHF.

Intermediate

Labeling Experience

AI Data Trainer & RLHF Annotator | Freelance Contractor (AI Platforms)

TextRLHF
As an AI Data Trainer and RLHF Annotator, I evaluated AI outputs by providing expert-level preference ratings and detailed logical justifications. I authored comprehensive rationales to clarify model instruction-following, truthfulness, safety, and tone boundaries. I generated 'Gold Standard' rewrites for incorrect responses to be used in Supervised Fine-Tuning datasets. • Processed over 90 complex reasoning cases in single 12-hour work sprints with zero rejection. • Rated outputs across multi-dimensional scales, distinguishing nuanced failures such as hallucinations and stylistic errors. • Flagged critical model failures in Portuguese-English translation and ensured model guidance improvements. • Created direct training data to fine-tune model completions within a structured workflow.

As an AI Data Trainer and RLHF Annotator, I evaluated AI outputs by providing expert-level preference ratings and detailed logical justifications. I authored comprehensive rationales to clarify model instruction-following, truthfulness, safety, and tone boundaries. I generated 'Gold Standard' rewrites for incorrect responses to be used in Supervised Fine-Tuning datasets. • Processed over 90 complex reasoning cases in single 12-hour work sprints with zero rejection. • Rated outputs across multi-dimensional scales, distinguishing nuanced failures such as hallucinations and stylistic errors. • Flagged critical model failures in Portuguese-English translation and ensured model guidance improvements. • Created direct training data to fine-tune model completions within a structured workflow.

2024 - Present

Education

S

SAS Institute

Certificate in Visual Analytics, Visual Analytics

Certificate in Visual Analytics
2024 - 2024
U

University of Pennsylvania

Certificate in Compliance, Compliance

Certificate in Compliance
2024 - 2024

Work History

S

Self-Employed

Linguistic Project Manager

Jundiaí
2019 - 2023
T

TV Leilão

Digital Asset QA Specialist

Jundiaí
2017 - 2018