Senior AI/ML Engineer — Real-Time Fraud Detection (Hybrid)

Adobe; New York (NY); Hybrid; USD 183,000 - 265,000; Full time

Benefits offered by this job

Hybrid work model

Job summary

Adobe is seeking a Senior AI/ML Engineer to build and scale fraud detection systems across signals, models, and production deployment. You will own end-to-end solutions from feature signals to real-time decisioning, applying LLMs and AI agents to expand detection capabilities and mitigate abuse.

You will collaborate with engineering, product, and risk teams in a hybrid New York setting, leveraging PyTorch, Python, and SQL to deliver high‑precision risk scoring and scalable risk signals.

Qualifications

• 8+ years building and operating production ML systems in adversarial domains.
• Strong Python, SQL, and PyTorch experience.
• Experience guiding ML systems from feature engineering to production deployment.

Responsibilities

• Build and deploy high-precision ML models for fraud and abuse detection, anomaly detection, and risk scoring.
• Engineer risk signals from large-scale data (accounts, devices, networks, behavior).
• Integrate ML/AI features into real-time risk decisioning and automated enforcement.
• Apply LLMs and AI agents to expand detection, investigation, and classification capabilities.
• Translate emerging attack patterns into new models, signals and mitigations.
• Evaluate solutions for accuracy, latency, cost, and customer impact.
• Own model evaluation, monitoring, and drift as attacker behavior evolves.
• Partner with engineering, product, and risk teams to ship production-ready capabilities.

Skills

ML systems

Python

SQL

PyTorch

LLMs / AI agents

Fraud domain

Bachelor's degree

Education

Bachelor's degree in CS/Statistics/Math

Advanced degree a plus

Tools

PyTorch

Job description

Adobe is seeking a Senior AI/ML Engineer to build and scale fraud detection systems across signals, models, and production deployment. You will own end-to-end solutions from feature signals to real-time decisioning, applying LLMs and AI agents to expand detection capabilities and mitigate abuse.

You will collaborate with engineering, product, and risk teams in a hybrid New York setting, leveraging PyTorch, Python, and SQL to deliver high‑precision risk scoring and scalable risk signals.