Data Scientist

Skills
DriftInterest RatesLabelsMicrosoft SurfaceModelingPhilanthropyProperty Management Systems
Role

What the job involves

The main requirements, responsibilities and hiring steps.

Requirements

  • 3-5 years of relevant experience
  • Strong generalist applied data science background
  • Strong Python and SQL
  • Experience with large production datasets in Starburst/Trino and Snowflake
  • Working knowledge of AWS
  • Experience measuring model performance on real-world production data
  • Ability to build ground truth where labels do not exist
  • Ability to detect drift and degradation
  • Comfort building and maintaining Streamlit dashboards
  • Ability to take a fuzzy question to a prototype and recommendation
  • Sound statistical judgment including sampling and error rates
  • Strong communication and ability to work embedded in another team
  • Willingness to perform other duties and special projects as needed
  • Sensitivity and respect for racial gender sexual orientation and cultural differences
  • Commitment to Candid values driven direct accessible curious and inclusive

Nice to have

  • resourceful
  • creative
  • conscientious
  • detail-oriented
  • independent
  • curious
  • inclusive

Day to day

  • Apply machine learning across data-quality and data-product problems, including detection, classification, entity resolution, anomaly detection, embeddings, semantic search, and feature engineering.
  • Measure how models perform on real production data, build ground truth where labels do not exist, and identify drift or degradation over time.
  • Work independently on project-defined scopes with product or data teams, prototyping solutions, building dashboards and tooling, and turning open-ended questions into clear recommendations.