Description:

Build and operate a real-time inference service for risk decisioning with low latency and high availability.
Own model deployment infrastructure including registry, CI/CD, and performance checks.
Develop model observability features such as monitoring and drift detection.
Collaborate with Risk Data Science for model handoff and production operation.
Implement experimentation capabilities and explainability outputs.
Take ownership of product development and contribute to building a new platform team.

Requirements:

5+ years in machine learning engineering, backend software engineering, or MLOps.
Experience in deploying and operating production ML services in low-latency contexts.
Strong backend engineering skills in Python with API frameworks like FastAPI or Flask.
Familiarity with model deployment tools, CI/CD, and versioning.
Experience in building observability and alerting for production services.
Knowledge of SQL and low-latency data stores (e.g., Redis, DynamoDB).

Competitive base salary and equity (stock options/RSUs).
Salary range for US employees: $166,600 - $208,300 USD; for Canadian employees: $157,400 - $196,800 CAD.

Skills

Benefits