Growth Platform ML Engineer — Personalization & Recommendations

Stripe; New York (NY); Hybrid; USD 180,000 - 270,000; Full time

Benefits offered by this job

Equity

401(k) plan

Medical, dental, and vision benefits

Wellness stipend

Job summary

Stripe is seeking a machine learning engineer to join Growth Platform. You will design, train, deploy, and monitor models that power product recommendations and personalized actions for Stripe customers.

You will collaborate with data scientists, engineers, product, and marketing to turn model improvements into business outcomes. You will work across problem definition, feature development, training, evaluation, deployment, and iteration, with a focus on reliability, latency, and cost.

Qualifications

• 3+ years in ML or data science in production.
• Strong Python programming and testable production code.
• Experience with PyTorch, TensorFlow, XGBoost, or scikit-learn.
• Experience building data/feature pipelines; SQL proficient; Spark/PySpark.
• Solid understanding of statistics, model evaluation and experiments.
• Experience deploying, monitoring, and debugging production ML systems.

Responsibilities

• Build and operate production ML systems for recommendations and personalization.
• Own problem definition, feature development, training, deployment and iteration.
• Collaborate with data scientists, engineers, and product partners to drive outcomes.
• Design data and feature pipelines and improve data freshness.
• Develop tooling for model evaluation, retraining, and safe rollout.
• Monitor and tune models for reliability, latency and cost.

Skills

ML engineering

Python

ML frameworks

SQL

Spark

Statistics

Production ML

Collaboration

Deploy & monitor

Job description

Stripe is seeking a machine learning engineer to join Growth Platform. You will design, train, deploy, and monitor models that power product recommendations and personalized actions for Stripe customers.

You will collaborate with data scientists, engineers, product, and marketing to turn model improvements into business outcomes. You will work across problem definition, feature development, training, evaluation, deployment, and iteration, with a focus on reliability, latency, and cost.