Senior Machine Learning Engineer

Sao PauloPermanent - full timesenior

Machine Learning EngineerData

0 views0 saves0 applied

Apply Now

Quick Summary

Overview

At PPRO, our mission is to simplify access to local payment methods and our vision is to enable the sale of goods and services to anyone in the world using their preferred way to pay.

Technical Tools

Machine Learning EngineerData

At PPRO, our mission is to simplify access to local payment methods and our vision is to enable the sale of goods and services to anyone in the world using their preferred way to pay. We empower partners such as Ant Group, PayPal and Stripe to access new markets, connect with more customers, and accelerate their growth.

Our strength lies in our diverse global team with 50+ nationalities and 10+ international locations- all united around one goal – to deliver the best possible products and services to our partners and customers. While our company mission is to keep innovating global commerce, our internal mission is to #chooseaction, #beopen, #thinkcustomer, #gofurther and #wintogether

The Purpose:

As a Machine Learning Engineer in PPRO’s Performance Powerhouse team, you will take ownership of building and deploying intelligent systems designed to maximize transaction approval rates and minimize false declines.

You will partner with Product Managers, Data Analysts, and Core Payments Engineers to develop real-time predictive models that dynamically route transactions, optimize retry strategies, and adapt to issuer behaviors across the globe.

This role is designed for experienced ML practitioners who can seamlessly bridge the gap between data science and software engineering.
It provides the opportunity to directly impact the company's bottom line by ensuring millions of legitimate transactions are successfully processed, while also offering the flexibility to grow into technical leadership or specialized ML architecture roles.

Develop and Deploy ML Models: Build, train, and deploy robust machine learning models focused on card authorization optimization, dynamic routing, and intelligent retries.

Real-Time Inference Engineering: Design and maintain low-latency inference pipelines capable of scoring live payment transactions within strict millisecond SLAs.

Feature Engineering & MLOps: Collaborate with data teams to build scalable feature stores, ensuring data quality, and automate model training/deployment pipelines (CI/CD for ML).

Experimentation & Shadow Testing: Drive A/B testing and shadow deployment strategies to safely measure the real-world impact of your models on live traffic and revenue.

Model Monitoring: Define and monitor key performance metrics to detect data drift, model degradation, and anomalies in production environments.

Classical & Deep Learning Mastery: Deep practical expertise in designing and tuning high-performance classical ML models (e.g. XGBoost, LightGBM, Random Forests) as well as experience with deep learning.

Ability to rigorously evaluate the trade-offs between model complexity and inference latency as well as experience beyond standard accuracy metrics utilising calibration curves, cost-sensitive learning, and precision-recall trade-offs.

Software Engineering & Python: Software engineering best practices, Python mastery and experience with the standard ML/Data libraries (Scikit-Learn, Pandas, Numpy) with a strong focus on writing scalable, production-ready code.

Real-Time Systems: Proven ability to build, deploy, and optimize ML models that operate under strict latency and high-throughput constraints.

MLOps Proficiency: Experience taking models from notebooks to production environments using tools like MLflow, Docker, Kubernetes, and CI/CD pipelines.

Strong SQL Proficiency: Ability to write complex queries and wrangle large-scale transactional datasets for feature extraction.

Payments Domain Knowledge (Nice to Have): Understanding of the card payment lifecycle, authorization processes, issuer behavior, 3D Secure, and network rules (Visa, Mastercard).

Cloud Infrastructure: Proven experience deploying and managing ML systems on AWS or similar, including expertise in infrastructure as code.