About the job
Become part of our team as a Machine Learning Engineer, contributing to the Adobe Risk Platform by building and developing models to detect fraud and abusive account behaviour. Collaborate with senior engineers on the model lifecycle and feature engineering. Ideal for candidates with strong Python skills and experience in machine learning solutions.
Responsibilities
Help build and train ML models covering various fraud and abuse areas. These include financial transaction fraud, device-related deception, and account and identity abuse. The goal is a unified, continuously-updated trust and risk score.
Contribute to feature engineering across transaction, device, and behavioral event data.
Build and maintain feature pipelines on Databricks and Spark, transforming raw transaction and device event data into high-quality model inputs.
Help translate prototypes into production ML systems, working with senior engineers on scalability, reliability, and observability.
Support MLOps practices: experiment tracking, model versioning, CI/CD, and production monitoring.
Collaborate cross-functionally with data science, product, and platform teams to understand fraud and abuse patterns across Adobe's surfaces.
Stay ahead of advances in ML/AI, particularly in fraud detection and behavioral modeling, and bring relevant ideas to the team.
Qualifications
Minimum
Bachelor's degree in Computer Science, Machine Learning, Data Science, or related field (or equivalent experience).
5+ years of professional experience building and deploying ML solutions, or equivalent experience through internships, research, or personal projects.
Solid programming skills in Python, with hands-on experience in PyTorch, TensorFlow, scikit-learn, or similar frameworks.
Working understanding of the ML lifecycle — from data collection through deployment and monitoring.
Eagerness to learn model optimization, inference efficiency, and production system integration, with support from senior engineers on the team.
Preferred
Coursework, projects, or professional experience in any of: payment fraud, device fingerprinting, account takeover detection, anomaly detection, or graph-based modeling.
Exposure to sequence modeling, transformer architectures, or graph neural networks.
Familiarity with Databricks, Spark, or large-scale transactional/event pipelines.