Machine Learning Engineer, Growth Platform
Stripe · San Francisco
About this role
**Machine Learning Engineer, Growth Platform** **About the Role** Build and operate production ML systems that improve how Stripe recommends products, content, and next steps to businesses. Own work from problem definition through training, evaluation, deployment, monitoring, and iteration. **Key Responsibilities** • Design, train, evaluate, deploy, and maintain recommendation and ranking models • Improve contextual bandit and policy-learning approaches • Build agent-based recommendation capabilities using business context • Develop reliable data and feature pipelines for training and inference • Build reusable tooling for model evaluation, retraining, and safe rollout • Own quality and operation of ML components with monitoring and reliability focus • Design and analyze online experiments with guardrails for user experience • Partner with product engineering and ML infrastructure teams • Work with product, marketing, and sales to identify problems ML can solve **Minimum Requirements** • 3+ years in ML engineering, software engineering, or applied data science with production ML experience • Strong Python programming and production code experience • Hands-on ML model design, training, and evaluation (PyTorch, TensorFlow, XGBoost, scikit-learn) • Data/feature pipeline building, SQL proficiency, distributed processing tools (Spark/PySpark) • Strong statistics, model evaluation, and experimentation knowledge • Production ML deployment, monitoring, and debugging experience • Ability to translate business problems into technical approaches **Preferred Qualifications** • Recommendation systems, ranking, or personalization experience • Contextual bandits, policy learning, causal inference, or off-policy evaluation • LLM applications (extraction, embeddings, context-grounded recommendations) • Reusable ML capabilities across products/teams • Product growth or lifecycle messaging systems
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.