Open to opportunities

Danilo Barros

@danilobarros

LLM Evaluation Engineer and AI Data Systems lead, I build scalable benchmarks, task pipelines, and human-in-the-loop QA for LLMs.

Brazil

Message

What I'm looking for

I’m looking to lead evaluation and synthetic task-generation work end-to-end—building benchmarks, gold answers, rubrics, and human-in-the-loop QA—while collaborating with clients and teams to standardize delivery, improve quality, and scale reliable eval environments.

I’m an LLM Evaluation Engineer and AI Data Systems lead with hands-on experience building, curating, reviewing, and scaling high-quality datasets, benchmarks, task pipelines, and evaluation workflows for large language models.

I grew at Turing from AI Trainer to Engineering Manager, leading remote teams across LLM benchmarking, task generation, data curation, rubric design, reviewer calibration, QA, pilot documentation, and client-facing AI data delivery.

I’m a heavy user of Codex, Claude, and OpenAI tooling to accelerate task ideation, prompt iteration, error analysis, documentation, task review, and process automation—turning ambiguous client goals into precise task specs, rubrics, gold answers, and production-ready data workflows.

I also combine software engineering, NLP, computational linguistics, neuroscience research, and team leadership to deliver RLHF-style human-in-the-loop systems, consistent scoring, and evaluation environments that improve reliability and decision-making.

Experience

Work history, roles, and key accomplishments

Current

Engineering Manager (AI Data)

Current

Turing

Dec 2022 - Present (3 years 7 months)

Led remote cross-functional teams delivering AI data, LLM evaluation, and benchmarking projects. Translated client goals into task specifications, rubrics, annotation guidelines, QA workflows, and benchmark documentation, overseeing human-in-the-loop review and calibration.

LLM Evaluation Task Generation Annotations Reviewer Calibration Quality Audits Prompt Engineering Documentation Claude Codex OpenAI API Data Curation

Machine Learning Engineer

Alana AI

Oct 2022 - Feb 2023 (4 months)

Developed and deployed NLP solutions using SpaCy, knowledge graphs, and modular Python architectures. Integrated graph database structures to represent relationships and improve retrieval and downstream reasoning performance.

Machine Learning NLP SpaCy Knowledge Graphs Graph Databases Python Modular Architectures Performance

Data Scientist

Anota AI

Jan 2022 - Sep 2022 (8 months)

Built scalable ETL pipelines with Apache Airflow, MongoDB, and MySQL to support reliable ingestion, transformation, and analysis. Developed Rasa-based conversational AI chatbots and created dashboards/analytics to surface operational insights.

Data Science ETL Apache Airflow MongoDB MySQL Conversational AI Rasa Natural Language Understanding Dashboards Data Validation Analytics

Computational Linguist

Redação Nota 1000

Jan 2019 - Jun 2020 (1 year 5 months)

Designed an automated essay evaluation system using NLP to assess written language quality. Conducted data annotation for entity recognition and POS tagging and built linguistic analysis pipelines to support feedback and writing assessment.

Computational Linguistics NLP Python SpaCy scikit learn Data Annotation Assessment Writing

Education

Degrees, certifications, and relevant coursework

Universidade Federal do ABC

Master's in Computational Neuroscience, Computational Neuroscience

Conducted research on brain-body synchrony and EEG data analysis using MNE-Python, R, and MATLAB to deliver insights into brain states. Co-authored papers published in Medicine & Science in Sports & Exercise and other journals including Springer Nature and Perceptual and Motor Skills.