Open to opportunities

João Vitor Pinheiro

@joovitorpinheiro

Machine Learning / Data Engineer with 4+ years of experience in fintech lending and forecasting solutions in consulting.

Brazil

Message

What I'm looking for

I seek roles where I can build production ML pipelines, improve data platform reliability, and deliver measurable business impact while collaborating with cross-functional teams.

Proven ability to optimize large-scale ETL/Spark workloads that power credit, risk, and analytics products, ship and maintain end-to-end forecasting solutions, and implement randomized experiments on unsecured lending to drive credit policy and portfolio optimization. Delivered production-grade ML pipelines on the Azure Cloud ecosystem, as well as self-service analytics frameworks for internal teams that shorten reporting cycles, accelerate time-to-insight, and enable faster decisions.

Experience

Work history, roles, and key accomplishments

Current

Machine Learning Engineer

Current

Nubank

Sep 2022 - Present (3 years 3 months)

Refactored Lending valuation framework from Scala to Python, built PySpark pipelines and automated business sanity checks, reducing data landing time by 34 hours and accelerating lending decision workflows. Developed experimentation logic for A/B tests, low-code dashboards that cut weekly reporting from one day to 5 minutes, and automation for library deployment via GitHub Actions.

Python Pyspark Scala Databricks AWS S3 GitHub Actions Python Pptx

Data Scientist

EloGroup Consulting

Jun 2021 - Sep 2022 (1 year 3 months)

Delivered a forecasting solution for a major São Paulo gas distributor that reduced contractual fines and saved ~R$200M in the first three months by deploying ensemble models and end-to-end ML pipelines in Azure. Implemented clustering, LGBM, SARIMAX ensembles, and interactive Streamlit tools for stakeholders.

Databricks MLFlow Streamlit Azure Data Factory Power BI