Adobe is seeking a Machine Learning Engineer to join the Adobe Risk Platform (ARP) team. ARP is Adobe's centralized, adaptive system for detecting, preventing, and mitigating fraud and abuse across products and services - protecting surfaces like Commerce, Stock, and Firefly with real-time risk decisions, without degrading the customer experience.
In this position, you will help build and develop machine learning models to identify fraudulent activity, detect abusive account behavior, and protect the experience of hundreds of millions of users. You'll work across the model lifecycle from raw behavioral data and feature engineering, to model training, deployment, and monitoring alongside senior engineers on the team.
Key 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.
Minimum Qualifications- 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 Qualifications- 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.
Expected Pay Range:Our compensation reflects the cost of labor across several U.S. geographic markets, and we pay differently based on those defined markets. The U.S. pay range for this position is $151,800 - $265,350 annually. Pay within this range varies by work location and may also depend on job-related knowledge, skills, and experience. Your recruiter can share more about the specific salary range for the job location during the hiring process.In California, the pay range for this position is $183,300 - $265,350
At Adobe, for sales roles starting salaries are expressed as total target compensation (TTC = base + commission), and short-term incentives are in the form of sales commission plans. Non-sales roles starting salaries are expressed as base salary and short-term incentives are in the form of the Annual Incentive Plan (AIP).
In addition, certain roles may be eligible for long-term incentives in the form of a new hire equity award.
