Responsibilities

• Work on subscription, ads, and in-app LTV prediction services
• Ensure the efficiency, reliability, explainability, and observability of ML pipelines
• Build and maintain ETL workflows and query large tables
• Detect anomalies, data drifts, and prediction shifts and partner with user acquisition managers on investigations
• Collaborate with data engineers to detect data quality issues
• Participate in generative AI projects

Nice to have

• Familiarity with MLOps tools and the Databricks platform
• Experience building REST APIs and working with real-time streaming data
• Experience with recommendation systems, NLP/LLMs, or other generative AI
• Familiarity with subscription-based product data

Requirements

• Hands-on experience with machine learning modeling and a good understanding of ML fundamentals
• Proficiency in Python software engineering (parallel/asynchronous computing, unit testing, CI/CD, etc.)
• Solid grounding in statistics and experimental design
• Advanced SQL skills and experience working with large datasets, ETL workflows, and scheduling pipelines (e.g., Airflow)
• Experience using BI tools (Tableau, Power BI, and Looker) for data visualization