Kinsa is looking for a Data Scientist to join our Data Team, which is responsible for creating novel illness signals and forecasts from Kinsa’s illness data. These illness signals drive unique insights for our customers (e.g. local public health officials, illness product companies), allowing them to take action against spreading illness (e.g. mobilizing diagnostic testing units, stocking illness products in regions with rising illness). This position will be responsible for revamping our illness signals infrastructure and pipeline, allowing us to scale and deliver insights to more customers. You will work cross-functionally with other data folk (scientists, analysts, and engineers) as well as product managers to design, deliver, and iterate on solutions, as new use cases come up.

Kinsa was founded with a mission to stop illness from spreading by knowing where and when it starts. Our mission has never been more important or more relevant than it is right now. We are leading the charge in the fight against COVID-19. Our real-time map of illness has been featured in the New York Times, on Rachel Maddow, CNBC, FOX News, The Economist, The Daily Show with Trevor Noah etc. Turn on the TV, open the paper… We are making headlines bringing our Data to the fight. We’ve done this by successfully transforming the first device you grab when sickness strikes - the thermometer - into a sensor to detect when and where illness is rising, and communicate with those who have just fallen ill.

A few example projects you may tackle in this role:

• Design and build a modular signal processing pipeline (with steps such as geosmoothing, demographic-stratification, etc.) that allows for flexible illness signal generation for different use cases
• Implement and evaluate the performance of different forecasting models to create geographically-specific illness forecasts from Kinsa's historical illness signals
• Explore research questions with Kinsa’s illness data, e.g. how does illness spread within schools or households? These explorations often turn into production-ready signals/capabilities
• Brainstorm and test out strategies to mitigate the effect of rapidly changing user demographics or user behavior on illness signals
• Run Monte Carlo simulations to determine the minimum number of thermometers needed in a given geography for hyper-local (sub-county level) outbreak detection

About you:

• Have a bachelor’s or advanced degree in data science, computer science, engineering, statistics, or other related field
• Have 2+ years in a data science role, with experience designing data pipelines and writing production python code
• Have experience with DS/ML packages, such as pandas, numpy, and scikitlearn
• Have excellent written and oral communication skills, and be able to explain the impact and details of your work to both technical and non-technical audiences
• Be excited about working in a fast-paced, fast-changing environment, juggling multiple priorities
• Feel comfortable solving ambiguous problems and thinking under pressure, both individually and in cross-functional teams
• Be the type of person who jumps in to solve spontaneously arising problems, even when not directly related to your immediate work
• Enjoy learning and sharing your unique knowledge and skills with other team members

You might also have:

• Experience with time-series analysis/forecasting
• Experience working with geospatial data (e.g. geopandas)
• Experience with tools such AWS and airflow

About Us:

Be Committed: We are committed to our mission. We have a tremendous opportunity in front of us: to change the face of public health and save hundreds of thousands of lives in the process. We are committed to working hard, working smart, working together, and doing what it takes to make a difference. Our time is now.