Data Scientist

About Serif Health:

Serif Health is a YCombinator-backed startup dedicated to increasing transparency and lowering costs in the United States healthcare system. Our world class team aggregates, enhances, and distributes billions of healthcare pricing data points each month for a sizable list of B2B & Enterprise customers. Thanks to our tight focus and high level of expertise, we have strong paid customer traction, high NPS and inbound referral rates, and a top 1% balance sheet.

We are excited to add new team members motivated by our mission, passionate about making a difference in healthcare, and who have a track record of being the best at what they do.

What You’ll Do:

• Perform statistical analysis of trillions of data points across our data sets to uncover actionable insights
• Build predictive models, algorithms, and analytical frameworks based on your observations that can be productized for our customers
• Design, build and sustain clustering, NLP, and outlier detection algorithms and/or machine learning models that can classify, link, and de-noise healthcare pricing data points across data sets and over time
• Collaboratively define the data architecture and delivery processes for our company, and ensure our customer pipeline can scale and grow profitably relative to the size of our team.
• Keep abreast of industry developments and best practices in data science and engineering

What we expect:

• At least 5 years of academic and/or commercial experience in a healthcare data science and analytics role
• Proficiency in Python and SQL for data manipulation and analysis.
• Experience with statistical modeling, machine learning, and data visualization tools (e.g., TensorFlow, Pandas, Scikit-Learn, PyTorch, and Keras or similar).
• Comfort working with large-scale datasets (2TB+, 300B+ rows added monthly) and distributed computing platforms like Databricks/Spark for large-scale data transformation and model training.
• A track record of solving complex, unstructured problems with creativity and precision.
• Strong communication skills and the ability to present data-driven narratives to stakeholders at all levels.
• An ability to work independently, move quickly, and self-manage for high impact in a small team environment.
• High attention to detail, strong written and verbal communication skills, and professionalism
• Passion for problem solving and increasing affordability & transparency in the US healthcare market

What we'd love to see (Bonus):

• Experience working with any of the following data: electronic medical records, medical claims and explanation of benefits, healthcare billing / coding / pricing
• Prior experience working in a startup or small team environment
• Familiarity with Amazon AWS data science & ML stack
• Prior experience in roles requiring direct interaction with customers

Job Location:

Anywhere in the U.S. - Serif Health is a remote-first company with team members coast-to-coast. We hold on-sites at least quarterly in rotating locations across the U.S. for team members to get to know each other and collaborate in-person.

Our initial interview is a takehome, giving you the time, space, and comfort to show your best work and ability to work independently and communicate solutions asynchronously. It will cover real-world problems we see in the existing transparency data space.

Followup technical interviews, will cover a few pragmatic topics. These are open-ended and we don’t necessarily have solutions to them. We’d love to understand the process you’d take to solve these, understand your creative & problem solving process, and hopefully get you excited about the challenges we’re working on.

For the team fit interview, you'll meet other members of our engineering and leadership teams who you'd be working with on a day-to-day basis. These are a chance to understand our working style and our motivations for working in this space.