Data Scientist

As a Data Scientist, you will work with Pie’s analytics, underwriting, and data engineering teams as well as 3rd party data providers, to develop, maintain, and enhance our feature engineering, automated data pipelines, modeling datasets, and other Data Assets. You will wrangle data, hypothesize and test novel features, and automated validation pipelines and predictive analytic model building, deployment, and monitoring capabilities. Working with your team, you will build modeling solutions with strategic impacts.

How You’ll Do It

This position will be working closely with our analytics, data engineering and MLOps teams to identify, acquire, validate, cleanse, and produce analytics datasets, predictive features, and modeling solutions, optimally in automated and reusable formats. This is accomplished by combining data processing experience, exploratory analysis, feature engineering, and data science practices into building data products.

Essential Duties and Responsibilities

• Understand analytics & modeling needs and build validated data pipelines to extract data, conduct exploratory analysis, build new predictive features, and help with the validation of ML models.
• Work with data engineers and the IT department to find the right data sources and ensure data quality and consistency.
• Build and maintain scalable data processing systems to support data science workflows
• Develop and implement feature engineering strategies to extract meaningful features from raw data and optimize model performance.
• Conduct data cleaning, transformation, and normalization to prepare data for analysis.
• Assist in building and deploying machine learning models and specialized AI models into the operations of the organization.
• Continuously monitor and evaluate the performance of models to identify areas for improvement.

The Right Stuff

• 3+ years experience as a Data Scientist or Sr. Data Analyst building and delivering data solutions for a company who uses data as a primary part of its business.
• 3 years experience Python programming
• Experience with cloud data warehouse
• Strong experience in writing complex SQL programming/queries
• Exposure to one major SQL RDBMS or analytics database (Snowflake, Redshift, MySQL, Postgres, Oracle, SQL Server, etc.)
• Deep experience in data wrangling: data extraction, transformation, and cleansing, data profiling and visualization, analytical prep-work for predictive modeling, automated data validation
• Experience with end-to-end product development using machine learning algorithms and techniques, including supervised and unsupervised learning, classification, regression, clustering, and deep learning.
• Fostering continuous delivery pipelines
• Managing and maintaining metadata
• Work in a fast-paced environment as part of a small team
• Collaborate with team members in the development and maintenance of our solutions
• Identify opportunities to automate data wrangling and analytics tasks and workflow
• Manage and maintain metadata and corresponding data dictionaries
• Build, enhance, and validate modeling datasets
• Experience with data processing frameworks and tools such as Spark/databricks, Snowflake, and SQL databases is preferred
• Familiarity with data visualization tools such as Tableau, Power BI, Dash, or matplotlib is preferred
• High School diploma or GED required, Bachelor’s Degree is preferred.