Insight Cloud is the intelligence platform for the modern analyst. It combines analytics apps from the industry's leading publishers with AI agents to deliver answers you can't get anywhere else, instantly.

Our Data Science team builds the models behind that intelligence and insights. Your work will involve exploring subscriber and publisher data sets, improving existing apps, developing analytical models, and applying machine learning techniques to uncover trends, patterns, and insights that generate significant improvements to industry-wide practices. You will collaborate closely with stakeholders to build and launch new analytics apps, ensuring the insights generated are delivered through Insight Cloud.

What you'll be doing

• Analyze large, sparse, and messy datasets to extract meaningful patterns, trends, and insights using advanced statistical methods and machine learning algorithms.
• Construct and maintain data processing workflows, ensuring efficient mapping and transformation of source data.
• Perform data enrichment by sourcing additional datasets and integrating them with publisher data to enhance analytical depth and accuracy.
• Develop complex queries and scripts to transform and model data, tailoring configurations and fine-tuning parameters for optimal performance.
• Translate business challenges into analytical frameworks, proposing and implementing data-driven solutions that have a tangible impact on our subscribers’ decision-making processes.
• Assist our BI Developers in creating interactive dashboards that provide intuitive visualizations of data insights, enabling users to derive clear, actionable information.
• Work closely with BI developers, data engineers, other data scientists and business stakeholders to ensure that models are aligned with business goals and technical requirements.
• Write clear and comprehensive documentation for models, pipelines, and workflows to facilitate collaboration and reproducibility.

Requirements

• 1+ year of experience in data science or data analytics
• Proficiency in common data science Python libraries for data transformation, regression, classification, and clustering
• Experience in data prep and feature engineering including cleaning, normalizing, transforming, and selecting relevant features from raw data
• Proficient SQL skills: joins, subqueries, window functions, common table expressions (CTEs), aggregations, complex string manipulations, stored procedures and functions
• Experience with data visualization tools and techniques or dashboarding products
• Excellent problem-solving and creative thinking skills with ability to drive complex data analysis and development forward independently
• Strong communication skills with the ability to present data and articulate complex technical concepts clearly and concisely
• Bachelor's degree in data science, statistics, computer science, or a related field.

Preferred Experience

• Experience with PySpark or SnowPark for Python, SQL user-defined functions and table functions (UDFs & UDTFs)
• Familiar with version control like GitHub or Gitlab and production deployment pipelines
• Experience working with large-scale datasets directly within cloud data warehouses such as Snowflake, DataBricks, or Redshift
• ML performance optimization experience: efficient computation, parallel processing, hyperparameter turning, model pruning, and quantization