Henrique Lopes

Data Scientist · Machine Learning · Python · SQL · AWS

Data scientist and engineer with experience since 2018 across fintech, health, consumer goods and cloud cost optimization. I build reliable data pipelines and the statistical analysis that sits on top of them, and I'm currently studying Pure Mathematics alongside work.

Also live in your terminal ssh henriquelop.es

Terminal

the SSH version, running in your browser
henriquelop.es — ssh

Click it, then use ← →, 1–6 and ↑ ↓, same keys as over SSH.

Years working with data

8.3

and counting, live

Roles
8
Project Euler problems
115+
Certifications
2

Now: Senior Data Analyst at Autodesk

Up next

Career timeline

select a bar to read the role
Senior Data Analyst, Autodesk Aug 2026 – present

Remote

  • Developed and maintained analytical data workflows supporting reliable, scalable analysis across datasets
  • Improved data quality and reliability through validation and observability controls, ensuring accurate inputs for downstream analytics and reporting
  • Analyzed and resolved data issues in production workflows, improving the consistency and reliability of data used for analytical decision-making
Senior Data Analyst, DbSeer Sep 2025 – May 2026

Remote

  • Led migration of a SQL Server-based data pipeline to a Python architecture, enabling scalable analytical workflows and improved data accessibility
  • Translated legacy procedures into optimized Python code, improving performance and enabling downstream statistical analysis
  • Improved observability and reliability of data systems, reducing downtime and enhancing analytical consistency
Senior Software Engineer, Wex May 2025 – Sep 2025

Remote

  • Led development of a modern data ingestion pipeline for large-scale payment and credit card data using Python and Apache Airflow, ensuring compliance with data security standards and improving scalability and maintainability
  • Implemented monitoring and observability improvements across microservices handling sensitive financial transaction data, strengthening data integrity controls and enabling early detection of anomalies and quality issues
Senior Data Analyst, PepsiCo Nov 2023 – Dec 2024

Remote

  • Conducted exploratory data analysis (EDA) and validation on large-scale datasets, identifying inconsistencies and improving data reliability
  • Reverse-engineered dbt models to map feature-level dependencies, enhancing data lineage and supporting analytical use cases
  • Integrated logistics and e-commerce datasets, enabling cross-domain analysis and improving operational decision-making
Senior Software Engineer, Virtasant May 2023 – Aug 2023

Remote

  • Developed Python-based analytical models to evaluate cloud usage patterns, applying statistical analysis to identify cost optimization opportunities (up to 80% savings)
  • Built ETL pipelines to preprocess and structure large-scale data, enabling downstream analytics and reporting
Data Engineer, Color Health May 2021 – Mar 2023

Remote

  • Designed and optimized ETL pipelines supporting large-scale analytical workloads in Google BigQuery
  • Migrated legacy pipelines to dbt and Airflow, improving performance, reliability, and analytical usability
  • Enabled data accessibility for downstream analysis through scalable and well-structured data systems
Data Analyst, BoldMetrics Inc. Jun 2020 – Aug 2021

Remote

  • Developed data ingestion and preprocessing pipelines for customer datasets, supporting machine learning model training workflows
  • Contributed to API and logging improvements, enabling more efficient data processing and analysis
  • Automated data preparation processes, improving efficiency in model development pipelines
Data Analyst and Engineer, Warren Investimentos Jun 2018 – May 2020

Porto Alegre, Brazil

  • Developed customer segmentation models and churn analysis using SQL and Python, enabling targeted business strategies and improved customer retention
  • Built and maintained a data lake and data warehouse architecture for large-scale analytics
  • Implemented event-tracking pipelines and enabled exploratory data analysis across multiple business domains
  • Defined key business metrics, enabling data-driven decision-making across teams

Projects

Portfolio Optimization (Markowitz Efficient Frontier)

NumPy, Pandas, SciPy, yfinance

The efficient frontier on a toy example: three made-up assets, short selling allowed. Hover the curve to see the mix of weights at each point.
  • Quantitative finance model implementing Modern Portfolio Theory to optimize asset allocation under risk constraints
  • Statistical estimation of expected returns and covariance matrices from historical time-series data
  • Formulated and solved a constrained quadratic optimization problem to compute the efficient frontier
  • Exploratory analysis of asset behavior and visualization of risk-return trade-offs

Project Euler

Algorithmic and mathematical problem solving

  • Solved 115+ computational problems combining mathematics and computer science
  • Applied algorithmic optimization, numerical methods, and analytical reasoning to complex problems

Toolkit

Programming

  • Python
  • Pandas
  • NumPy
  • SciPy
  • scikit-learn
  • SQL

Data Science

  • Statistical Analysis
  • Feature Engineering
  • EDA
  • Regression
  • Classification
  • Model Evaluation
  • Time Series Analysis
  • Optimization

Data Engineering

  • ETL Pipelines
  • Airflow
  • dbt
  • BigQuery
  • AWS S3
  • Athena
  • Glue

Visualization

  • Matplotlib
  • Data Analysis & Reporting

Concepts

  • Machine Learning
  • Data Modeling
  • Supervised & Unsupervised Learning
  • Reinforcement Learning

Tools

  • Git
  • Docker
  • Cloud Platforms

Education and certifications

Get in touch