# Matheus Cardoso

Matheus Cardoso is a remote worker on Himalayas, Data Scientist at Mercado Livre, based in Brazil.

Source: https://himalayas.app/@matheuscardoso

```text
Senior Data Scientist building GenAI and governed data pipelines for risk, discovery, and real-time decisions.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | Brazil |
| Authorized to work in | Brazil |
| Job categories | Data Scientist, Data Engineer, Machine Learning Engineer, Analytics Engineer, GenAI Data Scientist, Search Data Scientist, AI Data Scientist, ML Data Scientist, Research Data Scientist, Machine Learning Scientist |
| Skills | S3, Python, SQL, Pandas, NumPy, Polars, scikit learn, Keras, TensorFlow, PyTorch, LLM, RAG, Prompt Engineering, MLFlow, DBT, Apache Spark, PySpark, Kafka, Delta Lake, Docker, Kubernetes, Terraform, CI CD, Great Expectations, Datadog, Looker, Metabase, PostgreSQL, MongoDB, Redis, Hadoop, Hive, Apache Flink, AWS, AWS RedShift, AWS Glue, Dataflow, Prefect, Luigi, Java, Azure Data Factory, Azure Synapse, Google Cloud Platform, BigQuery, Google Cloud Dataproc, Cloud Composer, Dataplex, Vertex AI, GCS, Monte Carlo, Governance, Metadata Management, Data Cataloging, Data Modeling, Data Pipelines, Data Warehouse, Data Lake, Data Lakehouse, Real Time Streaming Data, Batch Processing, Airflow, Cassandra, Factory, Faiss, Gemini, GitHub, Method, MySQL, Lang Chain |

## What I'm looking for

```text
I’m looking for a role where I can lead GenAI and governed data pipeline initiatives—combining data modeling, metadata management, and privacy-safe architectures—to deliver reliable analytics, risk decisioning, and real-time intelligence.
```

## About

```text
I’m a Data Scientist focused on turning complex data into reliable decisions—especially where GenAI, privacy, and data governance must work together. I’ve led end-to-end solutions spanning modeling, pipeline engineering, and production-ready delivery.

At Mercado Livre, I led a financial data solution unifying receivables (future quotas, advances, and cash-flow views) to support the Financial Risk team. I also worked on Expected Credit Loss modeling for Mexico, concentrating on banking-regulation compliance with market simulators and expected loss/risk analyses.

My recent GenAI work includes building an advanced chatbot using Gemini and Claude LLMs with NER-based data anonymization to keep user data privacy-compliant. I implemented a federated learning architecture combining LLMs with knowledge graphs for confidentiality and personalization, and I built a vector-based Data Discovery Bot using LLM + Faiss + metadata that generated revenue for the business.

I bring strong data-engineering foundations for scale and reliability: real-time classification (e.g., NPS), GCP–AWS pipeline reconciliation, Airflow-based data-quality validation, and Spark pipelines detecting transformer failures in ~1B IoT records/hour to reduce downtime. I’m motivated by building governed, well-modeled systems that teams can trust and reuse.
```

## Experience

### Data Scientist (current)

Mercado Livre. May 2025 - Present

```text
Led development of a financial data solution unifying receivables (including future quotas), advances, and cash-flow views to support the Financial Risk team’s decision-making. Developed Expected Credit Loss (ECL) modeling for Mexico, including market simulators and expected loss/risk analyses for regulatory compliance.
```

Skills: Risk-And-Analytics, Financial-Modeling, Cash-Flow-Analysis, Regulatory-Compliance, Data-Pipelines, Decision-Support

### Data Scientist

Cloudevs. Jan 2024 - May 2025

```text
Built an advanced chatbot integrating Gemini and Claude LLMs, using NER-based data anonymization for privacy-compliant handling of user data. Implemented federated learning with LLMs and knowledge graphs to preserve confidentiality while improving personalization.
```

Skills: Claude, Anonymization, Knowledge-Graphs, Federated-Learning, Chatbot-Development

### Data Scientist

Tim Brasil. Mar 2023 - May 2025

```text
Built a vector-based chatbot (LLM + FAISS + metadata) as a Data Discovery Bot that generated R$2M in revenue for the company. Deployed a real-time NPS classifier integrating usage and billing data to support retention strategies.
```

Skills: LLM-Applications, Data-Discovery, Real-Time-NPS-Classification, Billing

### Data Scientist and Analytics Engineer

Stone Tech. Jan 2022 - Mar 2023

```text
Developed GCP-to-AWS pipelines for revenue and chargeback reconciliation. Created an Airflow-based data-quality validation system to improve robustness in high-volume pipelines.
```

Skills: Data-Pipelines, AWS, Data-Validation, ETL-ELT, Automation, Airflow

### Data Scientist

CPFL Paulista. Jan 2021 - Jan 2022

```text
Applied Transformer/BERT models to streamline inspection report analysis. Built a Spark-based model to detect transformer failures in ~1B IoT records per hour, reducing downtime.
```

Skills: Transformer-Models, BERT, NLP, Apache-Spark, IoT-Failure-Detection, Predictive-Maintenance, Data-Modeling

### Data Scientist

Robert Bosch LTDA. Feb 2019 - Dec 2020

```text
Developed asset-based analysis models for data failure prediction and clustering using IoT data. Built data processing workflows capable of handling over 1B lines of IoT data for downstream analytics.
```

Skills: Asset-Based-Analytics, Clustering, Machine-Learning, Data-Modeling, Predictive-Maintenance

## Education

### Universidade Federal do Rio de Janeiro (UFRJ)

Master Data Science and Analytics, Data Science and Analytics

```text
Master Data Science and Analytics with a thesis on applying LLMs to help a startup business plan using the Socratic method.
```

### Pontifícia Universidade Católica de Minas (PUC Minas)

Post Graduation in Machine Learning and Artificial Intelligence, Machine Learning and Artificial Intelligence

```text
Post graduation in Machine Learning and Artificial Intelligence.
```

### Centro Federal de Ensino Tecnológico Celso Suckow (CEFET/RJ)

Electrical Engineer (Electronics emphasis), Electrical Engineering

```text
Electrical Engineer with an electronics emphasis.
```

## Tech stack

- Azure Synapse
- Apache Spark
- AWS Glue
- Apache Flink
- Metabase
- Google Cloud Platform
- GitHub
- Kubernetes
- NumPy
- Pandas
- PySpark
- dbt
- MySQL
- PostgreSQL
- MongoDB
- Cassandra
- Hadoop
- Gmail
- Redis
- Terraform
- Java
- TensorFlow
- PyTorch
- MLflow
- scikit-learn
- Keras
- Kafka
- Datadog
- Gemini
- Airflow
- Luigi
- SQL
- LangChain
- Polars
- Monte Carlo
- Delta Lake
- Great Expectations
- Faiss
- Factory
- Remote
- Method
- Jan

To contact Matheus, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Guilherme Santos](https://himalayas.app/@guilhermesantos): Senior Data Engineer, Mercado Libre
- [Fernando Bascevicius](https://himalayas.app/@fbarscevicius): Tech Lead Machine Learning Engineer, Tricura Insurance Group
- [Açucena Rodrigues](https://himalayas.app/@aucenarodrigues): Founding AI Engineer, Coflint OÜ
- [Marcelo Dias](https://himalayas.app/@marcelodias): Owner / AI Engineer, VCM
- [Rodrigo Falcão](https://himalayas.app/@rodrigofalco): Data Scientist, A3Data
- [Francinei Gomes](https://himalayas.app/@francineigomes): Senior Python Developer, Thomson Reuters
- [Filipe Côrtes](https://himalayas.app/@filipecortes): Senior Data & AI Consultant, FC Consultoria E Servicos
- [Guilherme Tolentino](https://himalayas.app/@guilhermetolentino): Legal Consultant, Fundação de Desenvolvimento Gerencial
- [Abdul De Barros](https://himalayas.app/@abduldebarros): Analista Sênior de Customer Insights, Azul Linhas Aéreas
- [Micaelly Cristine](https://himalayas.app/@micaellycristine): Freelance Data Scientist & AI Engineer, Freelance
