Guilherme O.

Key Skills

Software

Don't disclose

Other

Top Subject Matter

Chatbot evaluation and generative AI output quality assessment

LLM response evaluation and quality assessment (self-directed)

Top Data Types

Text

Computer Code Programming

Top Task Types

Prompt + Response Writing (SFT)

Data Collection

Computer Programming/Coding

Evaluation/Rating

Transcription

Text Summarization

Freelancer Overview

AI-integrated chatbot assistant project (AIri) — reviewing and refining generative AI outputs. Brings 3+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose and Other. Education includes Technologist Degree, Uninove - Universidade Nove de Julho (2025). AI-training focus includes data types such as Computer Code, Programming, and Text and labeling workflows including Evaluation and Rating.

Labeling Experience

Daily use of generative AI tools for response quality evaluation

OtherText

Used generative AI tools (ChatGPT and Claude) on a daily basis for evaluating response quality and accuracy. Performed analytical checks for inconsistencies and guideline compliance when assessing generated content. Applied a methodical, detail-oriented approach to determining whether outputs met evaluation criteria. • Daily evaluation of generative AI responses for quality • Inconsistency detection within generated text • Accuracy assessment against implied guidelines • Consistent guideline-driven review workflow

2025 - Present

AI-integrated chatbot assistant project (AIri) — reviewing and refining generative AI outputs

Don't disclose

Developed an AI-integrated chatbot and performed iterative review of AI-generated outputs to ensure coherence and quality. Used generative AI tools and applied guideline-driven evaluation to identify inconsistencies and assess response accuracy during development. Refined responses to improve overall quality of the chatbot’s generated answers. • Evaluated chatbot response coherence against quality criteria • Detected and corrected inconsistencies in AI outputs • Assessed output accuracy prior to further integration • Iteratively refined prompts/API responses based on reviews

2024 - Present

Education

Work History