Staff+ Software Engineer, Account Abuse (Machine Learning)
$320k - $485k • San Francisco, CA | New York City, NY
Posted 8h ago
Job Location
San Francisco, CA | New York City, NY
Tech Stack
Remote Work Policy
On-site
Categories
Machine Learning Engineer
About the job
The Account Abuse team is responsible for ensuring Anthropic's computing capacity is allocated fairly by minimizing resources available to bad actors and preventing their return. As a software engineer on this team, you will build the machine learning systems that help detect and stop abuse at scale. This role involves classical ML on structured and behavioral data, focusing on training and shipping models where the stakes are real. You will build robust production systems, prioritizing measurement, precision, and safe rollout to avoid impacting legitimate customers.
Responsibilities
- Build and operate a feature computation platform for model training and real-time scoring with point-in-time correct data and low-latency retrieval.
- Train, evaluate, and deploy models to detect account-level abuse and fraud, running them both offline and online.
- Develop tooling to automate the model development lifecycle, including using Claude to accelerate feature development, training, and evaluation.
- Implement backtesting, shadow deployment, and staged rollout as default production paths, with monitoring for training/serving skew and adversarial adaptation.
- Collaborate with data scientists and the Policy & Enforcement team to enhance label coverage and quality.
- Partner with product and platform teams to gather signals and integrate model decisions with minimal impact on system latency, stability, or architecture.
Requirements
- Proficiency in Python and SQL.
- Experience training machine learning models and deploying them to production.
- Experience building data pipelines with a batch processing engine (e.g., Spark, Beam) and a workflow scheduler (e.g., Airflow).
- Working understanding of point-in-time correctness and training/serving skew, and methods to prevent them.
- Strong communication skills to explain technical tradeoffs to non-technical stakeholders.
Benefits
- Annual compensation range: $320,000 - $485,000 USD
- Visa sponsorship available