4 hours ago
London, United KingdomSenior
Responsibilities
- Design and build declarative, config-driven training pipelines for use by data scientists.
- Build unified model packaging and serving abstractions supporting multiple model types.
- Implement reproducible model evaluation frameworks with standardized metrics and automated validation gates.
- Build model monitoring for drift, performance degradation, automated retraining triggers, and audit trails.
- Integrate FinCrime-specific lifecycle tooling with Wise’s central ML infrastructure.
- Improve data science productivity and drive adoption of internal ML platform tooling.
Requirements
- Production experience building ML platform infrastructure such as training pipelines, model serving, evaluation frameworks, or monitoring systems.
- Strong software engineering fundamentals and experience with Python, Kotlin or Java, and SQL.
- Experience with ML orchestration tools such as Airflow or Kubeflow, model registries such as MLflow, and container-based deployment.
- End-to-end understanding of the ML lifecycle from data ingestion through training, packaging, serving, and monitoring.
- Experience with model serving at scale, latency optimization, ONNX packaging, or canary deployments is preferred.
- Experience in financial crime, fraud, AML, regulated environments, production model monitoring, drift detection, or ML workflow migration is preferred.
Benefits
- Starting salary of £87,500–£111,000 plus RSUs.
- Hybrid work arrangement.
- Wise benefits and an inclusive, international work environment.
About Wise
Wise builds a cross-border payments and multi-currency account used by individuals and businesses to send, receive, hold, and spend money in 40+ currencies. Revenue comes from transfer and account fees, card interchange, and enterprise partnerships via Wise Platform, which lets banks and large companies embed its international payments. Founded in 2011 as TransferWise, Wise is a London-headquartered public company.