Open to opportunities

Eduardo Seixas

@eduardoseixas

Message

I evaluate AI outputs and train reliable multilingual data workflows.

Brazil

Message

What I'm looking for

I'm looking for remote international work in AI evaluation, LLM quality, data training, multilingual QA, scientific content, education, or applied research. I value measurable criteria, transparent rationales, reproducible workflows, structured documentation, and responsible human-AI collaboration.

At FlyRank AI, I evaluate and improve AI-generated responses for clarity, reasoning, instruction-following, usefulness, and user-facing quality. I also support AI data-training workflows with SME Solutions Group / Blue Mantis and have completed model-evaluation projects for Mercor and Alignerr.

I've reviewed 140+ undergraduate theses for logic, evidence, conceptual accuracy, and readability, and trained 71 educators in AI literacy across Brazilian public-school networks. My work combines rubric-based evaluation, multilingual quality analysis in Portuguese, English, and German, scientific methodology, and structured feedback.

I'm especially interested in responsible AI education, technical content, and reproducible human-AI workflows. My applied research includes generative-AI workshops, ChemSketch learning interventions, Moodle learning objects, and AI-assisted visual evaluation.

Experience

Work history, roles, and key accomplishments

Current

AI Intern

Current

FlyRank AI

Jun 2026 - Present (2 months)

Evaluate and improve AI-generated responses in General AI Fluency tasks using structured criteria for clarity, reasoning, instruction-following, usefulness, and user-facing quality. Write concise, actionable feedback identifying gaps, inconsistencies, unsupported claims, and opportunities for improvement.

AI Evaluation Rubric Based Assessment Feedback Writing Prompt Analysis Quality Assurance

Current

AI Evaluation Contributor

Current

Alignerr

May 2026 - Present (3 months)

Contributed to an evaluation project involving aviation radio communication between pilots and air traffic control. Assessed speech and transcription ambiguity, overlap, temporal boundaries, and domain-specific interpretation in audio-related tasks.

Speech Recognition Transcription Audio Analysis Aviation Communication Data Evaluation

Current

Generalist AI Evaluator

Current

Mercor

May 2026 - Present (3 months)

Evaluated model outputs for reasoning quality, writing quality, factuality, and instruction-following. Compared responses using structured rubrics and delivered concise, evidence-based quality judgments.

AI Evaluation Reasoning Assessment Writing Quality Assessment Factuality Checking Instruction Following Rubric based Evaluation

Current

Data Trainer

Current

SME Solutions Group, Inc. / Blue Mantis

Mar 2026 - Present (5 months)

Performs data-training and quality-assessment tasks for AI-related workflows, including reviewing, categorizing, and evaluating textual data against project guidelines and quality criteria. Applies consistency, relevance, completeness, and accuracy checks to support dataset and model quality.

Data Training Quality Assessment data review Data Categorization Data Evaluation Quality Assurance AI Workflows