AI Quality Analyst – Portuguese (Remote)

About the role

We are looking for a Portuguese‑speaking AI Quality Analyst to join our short‑term project. You will work remotely, evaluating AI‑generated conversational responses and ensuring they are personalized, accurate, and helpful.

Key responsibilities

• Design and execute conversational prompts to test personalized AI interactions.
• Assess how well AI models use personal context to generate relevant responses.
• Evaluate model outputs for grounding, personalization accuracy, integration quality, and overall helpfulness.
• Compare and rank AI‑generated responses using predefined criteria.
• Identify hallucinations, flawed inferences, incorrect personalization, and unnatural behavior.
• Write clear, structured rationales supporting evaluation decisions.
• Review model debug information and verify proper use of data sources.
• Maintain data quality standards and follow project guidelines throughout the evaluation process.

Required profile

• Professional proficiency in reading and writing Portuguese.
• Experience in data annotation, AI quality evaluation, content moderation, or related fields.
• Strong analytical thinking, attention to detail, and excellent written communication.
• Ability to evaluate nuanced and ambiguous AI responses objectively.
• Comfortable working independently in a remote environment with a stable internet connection.
• Full‑time availability (30‑40 hours per week) with at least 4 hours overlap with PST.

Required skills

• Professional proficiency in Portuguese (reading and writing).