About this role
Building and operating production machine learning systems that improve how the organization recommends products, content, and next steps to businesses forms the core of the day-to-day work. The Growth Platform team creates shared recommendation and ranking models, contextual bandits, agent-based recommendations, and the evaluation pipelines powering surfaces like the Dashboard, email, onboarding, and AI agent interfaces. Operating successfully requires taking ownership of ambiguous problems from initial definition through feature development, deployment, monitoring, and iterative improvement. Practitioners who balance modeling expertise with software engineering skills, while collaborating closely with data scientists, product managers, and business partners, thrive in this environment.
What you will do
- Design, train, evaluate, deploy, and maintain recommendation, ranking, and personalized action selection models across various platform surfaces.
- Improve contextual bandit and policy-learning approaches by refining exploration, reward design, and adaptation to user context.
- Build agent-based recommendation capabilities and develop reliable data and feature pipelines for training and inference.
- Construct reusable tooling for model evaluation, retraining, and safe rollout to help the team ship improvements efficiently.
- Manage the quality and operation of production ML components by writing tested code, monitoring pipelines, and optimizing latency and cost.
- Design and analyze online experiments with data science partners to connect offline evaluations to product adoption.
- Partner with engineering, product, marketing, and sales teams to integrate models and identify problems solved by shared ML capabilities.
What you need
- Minimum of 3 years of industry experience in machine learning engineering, software engineering, or applied data science with production deployment history.
- Strong programming skills in Python with the ability to write maintainable and tested production code.
- Practical background in designing, training, and evaluating models using frameworks such as PyTorch, TensorFlow, XGBoost, or scikit-learn.
- Familiarity with building data or feature pipelines, SQL proficiency, and experience using distributed data processing tools like Spark or PySpark.
- Solid understanding of statistics, model evaluation, and experimentation, including avoiding data leakage and measuring business impact.
- Demonstrated ability to deploy, monitor, and debug production ML systems while balancing model quality, reliability, latency, and cost.
- Capacity to translate open-ended business problems into concrete technical approaches and collaborate across multiple disciplines.
Nice to have
- Experience with recommendation systems, ranking, personalization, or marketplace and advertising optimization.
- Experience with contextual bandits, policy learning, causal inference, or off-policy evaluation.
- Experience building and evaluating LLM applications, including structured extraction, embeddings, or context-grounded recommendations.
- Experience building reusable ML capabilities used by multiple products or teams, such as training automation or feature systems.
- Experience with product growth, lifecycle messaging, or systems balancing short-term engagement with long-term outcomes.
Skills and tech stack
Questions candidates ask
What surfaces do the recommendations reach?
Recommendations reach users across the Dashboard, email, onboarding, documentation, and AI agent interfaces. The team combines an understanding of each business with models that decide useful recommendations, timing, and outcome learning.
What does success look like in this role?
Success means helping businesses take useful actions and adopt products that help them grow, while keeping recommendations relevant and avoiding unnecessary messages. Practitioners own work from problem definition and feature development through training, evaluation, deployment, monitoring, and iteration.
What are the core technical requirements?
The role requires at least 3 years of industry experience in machine learning engineering, software engineering, or applied data science with hands-on production experience. Candidates need strong Python skills, practical ML framework usage, and familiarity with data pipelines, SQL, and distributed data processing tools like Spark.