Open to opportunities

Henrique Rodrigues

@henriquerodrigues

Message

Data engineering researcher integrating LLMs with semantic artifacts to improve data interoperability.

Brazil

Message

What I'm looking for

I’m looking for a role where I can leverage advanced research skills in LLM RDF/OWL/SPARQL integration and data engineering—building interoperable data pipelines, applying FAIR/Linked Open Data practices, and delivering measurable, impactful results.

I’m a highly motivated researcher focused on data management, interoperability, and Large Language Models (LLMs). My work combines data curation and standardization with FAIR Git principles and Linked Open Data, so the outputs are reusable and measurable—not just “working.”

In my Master’s research at UFRJ/PPGI (CAPES), I spearheaded study and implementation of LLMs integrated with SemanticArtifacts. I built an ontology-alignment pipeline in Python that vectorizes data via OWL2Vec and stores it in the QDrant vector database, then evaluated performance by comparing pure LLM approaches against adapter-based methods.

Earlier, as a ResearchAssistant at IBICT, I strengthened documentation and the organization of data assets to advance public data and interoperability initiatives. I supported curation, standardization, and metadata structuring tasks to enable seamless data integration between systems, while keeping quality and consistency front and center.

I also contributed to data repository operations and governance: at IBICT I deployed and maintained Dataverse repositories (LattesData, Aleia, Deposita Dados), managing metadata configuration and ingestion processes. Across my research assistant roles at RNP and my undergraduate research at CNPq/UFRJ, I documented workflows, produced descriptive statistics for curation and analysis, and deepened my understanding of RDF/OWL/SPARQL-oriented Linked Open Data and graph summarization.

Experience

Work history, roles, and key accomplishments

Current

LLM & SemanticArtifacts Research

Current

UFRJ/PPGI (CAPES)

Jul 2024 - Present (1 year 11 months)

Spearheaded Master’s research integrating Large Language Models with SemanticArtifacts. Built an ontology-alignment data pipeline using Python and OWL2Vec, vectorized data for storage in Qdrant, and benchmarked pure LLM approaches against adapter-based methods.

Large Language Models Ontology Alignment Python Qdrant Vector Databases Docker

Data Interoperability Research Assistant

IBICT

Aug 2023 - Jun 2024 (10 months)

Advanced public data and interoperability initiatives by strengthening documentation and organizing data assets. Supported curation, standardization, and metadata structuring to enable data integration between systems.

Data Curation Data Standardization Documentation Quality Assessment

Educational Data Research Assistant

RNP

Apr 2024 - May 2024 (1 month)

Assisted in organizing and technically describing educational datasets, reinforcing documentation and ensuring dataset consistency. Supported dataset curation activities to facilitate reliable reuse and integration.

Data Documentation Metadata Data Curation Quality Assurance Research Support

Educational Data Scholarship Holder

RNP

Feb 2023 - Jul 2023 (5 months)

Documented the educational data and metadata generation workflow using diagrammatic representations and standardized processes. Conducted quality assessment and descriptive statistics to support curation and analysis.

Workflow Documentation Metadata Data Standardization Diagramming Data Quality Descriptive Statistics Data Curation

Dataverse Repositories Research Assistant

IBICT

Mar 2022 - Feb 2023 (11 months)

Deployed and maintained Dataverse repositories (including LattesData, Aleia, and Deposita Dados), managing metadata configuration and ingestion processes. Improved dataset organization, governance, and availability to promote sharing and reuse.

Dataverse Metadata Management Data Ingestion Data Governance Data Curation Datasets Documentation

Linked Open Data Researcher

CNPq/UFRJ

Sep 2020 - Mar 2022 (1 year 6 months)

Explored Linked Open Data principles, database mapping techniques, information retrieval strategies, and graph summarization. Investigated approaches to represent and summarize graph-structured knowledge for research use.

Knowledge Graphs Data Mapping Information Retrieval Data Modeling

Education

Degrees, certifications, and relevant coursework

UFRJ (Universidade Federal do Rio de Janeiro)

Master's degree, Computer Science

2023 -

Master’s program in Computer Science focusing on integrating Large Language Models with SemanticArtifacts and building ontology-alignment data pipelines using OWL2Vec and vector storage/evaluation workflows.