Staff ML Engineer: Account Abuse & Fraud Detection

EngineersOfAI; San Francisco (CA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Anthropic is seeking a Software Engineer on the Account Abuse team to build ML systems for detecting and preventing account abuse at scale. You will develop a feature computation platform supporting model training and real-time scoring, ensuring point-in-time correctness and low-latency retrieval.

You will train and deploy models offline and online to protect users while maintaining robust production systems.

Qualifications

• Proficiency in Python and SQL.
• Experience training ML models and deploying to production.
• Experience building data pipelines with Spark or Beam and Airflow.
• Understanding of point-in-time correctness and training/serving skew.
• Strong communication skills to explain tradeoffs to non-technical stakeholders.

Responsibilities

• Build and operate a feature computation platform for model training and real-time scoring.
• Train, evaluate, and deploy models that detect account-level abuse and fraud.
• Build tooling to accelerate ML development, including Claude-assisted workflows.
• Implement backtesting, shadow deployment, and staged rollout with monitoring for skew and drift.
• Collaborate with data scientists and Policy & Enforcement to improve label quality.
• Partner with product and platform teams to minimize latency impact while integrating model decisions.

Skills

Python

SQL

ML training

Data pipelines

Point-in-time correctness

Communication

Tools

Spark

Beam

Airflow

Job description

Anthropic is seeking a Software Engineer on the Account Abuse team to build ML systems for detecting and preventing account abuse at scale. You will develop a feature computation platform supporting model training and real-time scoring, ensuring point-in-time correctness and low-latency retrieval.

You will train and deploy models offline and online to protect users while maintaining robust production systems.