CLEAR transforms what is uniquely you – your fingerprints, your face, your eyes – into a secure, biometric key to frictionless experiences. We are creating a world where travel is effortless, where accessing your office building is as simple as walking in, and where shopping is as easy as walking in and out of a store—without ever once showing an ID or credit card. CLEAR currently powers secure, frictionless customer experiences in nearly 40 U.S. airports and venues. With over 3 million members so far, CLEAR is the identity platform of the future, today.

Through cutting edge biometrics and advanced Homeland Security certified data algorithms, CLEAR products guarantee identity and protect our members, while speeding them through security. We’re seeking an innovative, intellectually curious and results-oriented Data Scientist to support, enhance and expand CLEAR’s current and projected security and identity algorithms. As a critical member of our research and development team, you will have a prominent voice in the future of our company. You’re a deep thinker who enjoys solving critical problems, and can own a solution from end to end.

You are technically proficient and have the ability to access and wrangle large amounts of structured and unstructured data, a great business sense, the desire to influence strategic decisions with data-driven analysis. You are passionate about applying data science towards solving business problems, particularly within the context of quantitative product features. You think deep, you happily prove your assumptions and you work fast. Lastly, you have strong written and verbal communication skills.

What You Will Do:

• Define data requirements and gather and validate information, applying judgment and statistical tests. Ability to prototype code for the newly researched methods to support the integration of new algorithms. Writing production ready code is a plus.
• Understand ground truth, create training models, devise new statistical models, using machine learning techniques within the context of domain specific and domain independent data.
• Work collaboratively with the data science and product management teams to evolve current and build new quantitative product features.
• Work collaboratively with engineering to integrate new product features into production.

Who You Are:

• You have a strong desire to work in a highly collaborative, team oriented, intellectually curious environment.
• Comfortable scoping and structuring your work in the face of a variety of different problems types such as deterministic problems, amorphous, ambiguous, and otherwise heuristic ones as well.
• Have at least an M.S. (preferred) or Bachelors (required) in Computer Science, Operations Research, Computational Economics, Statistics, Applied Mathematics, Data Science, or related major.
• Demonstrable hands-on experience in Machine learning (Bayesian Analysis, Decision Trees, Random Forests, Boosted Trees, Support Vector Machines, Neural Networks, etc.) and Advanced mathematics to create product features.
• 5+ years experience leveraging the Python Data Science stack (scikit-learn, Numpy, Pandas, etc.) to drive prototyping of large data sets. Experience with auto model building tools such as DataRobot, AutoML, et al. is highly desired.
• Experience managing your code in a modern day version control system, eg git.
• Experience modeling risk related problems, particularly those with class imbalances is highly preferred.
• Experience conceiving of new metrics based on synthesis of new and existing data is highly preferred.
• Skilled in cleaning, transforming and otherwise statistically describing data for the purpose of feature engineering. Experience with Feature Tools or similar is highly preferred.
• Proficient in leveraging a variety of visualization packages and applications such as Tableau, Looker, matplotlib, Python dash, plotly, et al. to expose meaningful insights in data.
• Experience working with data warehouses and/or relational databases and SQL in a real-world context. Experience with Snowflake is highly preferred.