Staff Data Scientist

We’re looking for data scientists to join our team. You'll develop statistical and machine learning models to improve our operations platform and help us provide a better service to our clients. We're looking for generalist data scientists who are excited to jump into new problems and write production-quality code. 

About the work:

• Leverage data to solve meaningful problems with appropriate complexity.
• Collaborate with a diverse team across engineering, PM, and care operations to define a strategy and execute against it.
• Research operational/logistical problems and proactively identify potential solutions.
• Lead the design, implementation, and evaluation of descriptive and predictive models.
• Integrate machine learning into user-facing applications.
• Mentor and provide technical oversight on teammates' projects throughout the project lifecycle.

About you: 

• Excellent communication skills with both technical and non-technical peers.
• Excellent mathematical and statistical fundamentals, including a degree in a quantitative field (such as Computer Science, Mathematics, Statistics, Economics, Physics) or equivalent professional experience.
• Wide-ranging professional experience solving complex business problems, and shipping/maintaining Python in a production environment.
• 5+ years of industry experience.
• Aptitude to rapidly iterate and deliver technical solutions that maximize business impact.
• Expertise with numerical software packages such as NumPy, scikit-learn, etc.
• Able to manage product ambiguity, seeking clarity when possible.
• Are accountable end-to-end for your own projects, through planning, deployment, maintenance, and monitoring. You spot and address potential issues early.

Bonus points if you have professional experience with: 

• Designing systems to optimize portfolio allocation in a two-sided marketplace (E.g., ideal matches of people needing and providing care, automated financial incentives to staff remaining shifts, hiring needs, demand forecasting, etc.)
• Using survival analysis and related methods to evaluate risk of employee churn and to predict future high-performers
• Using NLP methods to build data products from a variety of unstructured data sources, including phone calls and website forms
• Applying spatial statistics to incorporate geographic and regional differences in a variety of problem contexts