The opportunity
The Account Abuse team is tasked with ensuring Anthropic's computing capacity is allocated fairly, minimizing resources available to bad actors and preventing them from coming back. As a software engineer on this team, you will build the machine learning systems that help us detect and stop abuse at scale.
What you'll do
Build and operate a feature computation platform that serves both model: training and real-time scoring, with point-in-time correct training data and low-latency online retrieval
Train, evaluate, and deploy models that detect account-level abuse and fraud,: running them both offline and online
Build tooling that automates more of the model development lifecycle,: including using Claude to speed up feature development, training, and evaluation
Make backtesting, shadow deployment, and staged rollout the default path to: production, with monitoring for training / serving skew, drift, and adversarial adaptation
Work with our data scientists and our Policy & Enforcement team to improve label coverage and quality
Partner with product and platform teams to gather signals and integrate model: decisions with minimal impact on their systems' latency, stability, or overall architecture
What they're looking for
- Experience building or operating a feature platform such as Chronon, Feast, or Tecton
- Experience with stream processing engines such as Flink, Beam / Dataflow, or Kafka Streams
- Experience training ML models in a production setting with demanding serving: requirements, such as fraud, risk, or ranking
- Experience with tree-based models on tabular data
- Experience building unsupervised, clustering-based or graph-based detection: systems to surface coordinated account abuse
- Experience in integrity, spam, fraud, or abuse detection
- Experience working with scarce, delayed, or noisy labels
- Experience with AutoML or other approaches to automating the ML workflow
