Jerry is looking for an Applied Data Scientist to ensure the accuracy, reliability, and cleanliness of their data, transforming raw data into high-quality features for modeling and driving critical business decisions.
Requirements
- Strong proficiency in Python (Pandas/NumPy) and SQL for complex querying and data manipulation.
- Hands-on experience with data cleaning techniques and data validation frameworks.
- Familiarity with data visualization tools to help identify and communicate data issues.
Responsibilities
- Participate in the full modeling lifecycle, from statistical analysis and experimentation to building, validating, and iterating on machine learning models that address critical business challenges.
- Own the data foundation by preparing, cleaning and transforming raw, complex data into high-quality features for modeling.
- Proactively identify and handle missing values, outliers, and inconsistencies.
- Investigate data discrepancies (tracking bugs, ETL errors, definitional issues) and design automated frameworks to ensure data accuracy.
- Act as a strategic liaison, collaborating with data engineering and product teams to drive the data strategy and definition of our centralized feature store, ensuring it becomes the single source of truth for all ML models.
- Create and maintain clear, authoritative documentation for data sources, cleaning processes, and variable definitions.
Other
- Meticulously detail-obsessed Applied Data Scientist
- Passionate about the foundational layer of all data analysis: ensuring our data is clean, accurate, and reliable.
- Detective at heart, driven by deep curiosity to understand complex data systems, and you find immense satisfaction in transforming messy, ambiguous datasets into pristine assets that drive critical business decisions.
- Own the entire journey: from taking raw application data to generating clean inputs, to building models and delivering tangible value in real-world applications.
- Obsessed with details: You have an exceptional eye for detail and a low tolerance for errors. Accuracy and precision are non-negotiable.
- Strategic thinker: You can see the bigger picture and are passionate about building robust systems and processes that will stand the test of time.
- Proactive & persistent: You actively seek out data quality issues and persist until resolution.
- Curious & adaptive: You are inherently curious, comfortable with ambiguity, and skilled at breaking down complex problems.
