18 hours ago
Responsibilities
- Design, train, evaluate, deploy, and maintain recommendation, ranking, and personalized action-selection models.
- Improve contextual bandit and policy-learning approaches, including exploration, reward design, and adaptation to user feedback.
- Build agent-based recommendation capabilities and evaluations using business context.
- Develop reliable data and feature pipelines for model training and inference.
- Create reusable tooling for model evaluation, retraining, safe rollout, and experimentation.
- Write tested production code, monitor ML components and pipelines, investigate failures, and improve reliability, latency, and cost.
- Design and analyze online experiments and connect offline model evaluation to product adoption and incremental impact.
- Partner with product engineering and ML infrastructure teams to integrate and improve shared ML capabilities.
- Collaborate with product, marketing, and sales partners to identify valuable applications for shared ML systems.
Requirements
- At least 3 years of industry experience in machine learning engineering, software engineering, or applied data science, including hands-on production ML experience.
- Strong Python programming skills and experience writing maintainable, tested production code.
- Experience designing, training, and evaluating ML models with frameworks such as PyTorch, TensorFlow, XGBoost, or scikit-learn.
- Experience building data or feature pipelines, proficiency in SQL, and familiarity with Spark or PySpark.
- Strong understanding of statistics, model evaluation, and experimentation, including data leakage and business-impact analysis.
- Experience deploying, monitoring, and debugging production ML systems while balancing quality, reliability, latency, and cost.
- Ability to translate open-ended business problems into technical approaches and collaborate across engineering, data science, product, and business teams.
- Preferred: experience with recommendation systems, ranking, personalization, marketplace or advertising optimization, contextual bandits, policy learning, causal inference, or off-policy evaluation.
- Preferred: experience building LLM applications, reusable ML capabilities, training automation, feature systems, model monitoring, product growth, lifecycle messaging, or long-term user-outcome optimization.
Tech Stack
Categories
About Stripe
Stripe builds financial infrastructure for internet businesses, offering APIs and tools for online and in‑person payments, subscriptions, marketplaces/payouts, fraud prevention, identity, tax, issuing, and treasury. It monetizes through per‑transaction fees and SaaS pricing for advanced products. Founded in 2010 and headquartered in South San Francisco, Stripe is privately held and serves companies from startups to large enterprises worldwide.