CareYaya is looking to build data products that make it easier for older adults and families to get the help they need—when they need it, by turning messy, real-world data into simple, high-impact decisions.
Requirements
- Fluent in Python (pandas, NumPy), SQL, and Jupyter/Notebooks
- Know the basics of machine learning (scikit-learn), feature engineering, and model evaluation
- Can communicate results crisply with data visualization (Plotly/Matplotlib) and slide-worthy summaries
- Understand experiment design (A/B tests), causality basics, and common pitfalls
- Experience with dbt, cloud warehouses (BigQuery/Snowflake/Redshift), or Postgres
- Marketplace analytics, route/ETA modeling, or operations research
- NLP/LLM experience for text classification or quality scoring
Responsibilities
- Prototype and evaluate models that pair families with the right caregivers (availability, skills, distance, reliability)
- Create features and rules that improve platform integrity (no-shows, response times, quality flags)
- Forecast supply/demand by market; build cohort, retention, and funnel analyses to guide city launches
- Design/prioritize A/B tests; analyze lift and tradeoffs; recommend rollouts
- Build maintainable dashboards (e.g., marketplace health, SLA adherence) for non-technical teammates
- Rapid prototypes for profile quality checks, text classification, and support tooling
- Ship incrementally, document decisions, and measure outcomes
Other
- Care about the mission and can handle sensitive data with maturity (we follow strict privacy practices)
- Are organized and product-minded
- Prior work in healthcare, public health, aging, or social impact
- Meaningful problems with direct impact on families and caregivers
- Mentorship from a small, fast team that blends product, ops, and data
