Data Scientist

Full Time
Mid Level

About Pattern Data

At Pattern, we're building an intelligence platform that uses AI to accelerate and improve the accuracy of discovering and evaluating personal injury and mass tort cases. Along the way, we've created one of the world's largest repositories of health records for individuals in liability cases. We partner with the largest law firms in the US to transform how they understand and create new, actionable insights from litigation patterns. 

Our platform is cloud-native built using Scala on AWS. We select the best tools and infrastructure to power the industry's fastest and smartest document processing pipeline, turning terabytes of unstructured data into real-time, indexed medical knowledge bases, accessed via a React + TypeScript application. 

Please note, our offices are located in Charlotte and Richmond but this role can be remote 

The Role 

Pattern is dependent on robust, performant, and efficient models to power our platform. As a data scientist at Pattern, you will own and develop these models. You'll collaborate closely with our executive team, product managers, and backend developers to build state-of-the-art products driven by your models. You will be involved in high-level product and technical decision-making, as well as deep in the weeds to unlock those around you and write thoughtful, maintainable code. Your work will be deployed to legal teams at leading US law firms. At Pattern, we are looking for someone who displays the following skills: 

  • Ability to operate the full data science project lifecycle, from data retrieval, wrangling, model training, validation, through deployment and monitoring
  • Experience using a variety of natural language processing techniques, projects in the medical language domain are particularly relevant
  • Experience implementing and deploying models into highly performant, real-time applications, preferably using container (Docker) principles
  • Understand practical business implications when developing models, and is able to apply domain knowledge to maximize model outcomes
  • Ability to engage in an iterative approach to software development and striving to deliver value with every release
  • A team player with the willingness to work full-stack when it makes sense


  • Master’s degree in Operations Research, Industrial Engineering, Applied Mathematics, Statistics, Physics, Computer Science, or related fields OR 2+ years equivalent work experience in a comparable full-time data science position
  • Proficient with either Scala or Python
  • 2+ years experience using NLP techniques
  • Ideal candidates will be able to show samples of work for professional, educational, or personal projects

Core Tech Stack 

  • Scala
  • Python
  • React + TypeScript


Note: Successful candidates will be asked to undergo a background check 


Apply for this position

Apply with Indeed
We've received your resume. Click here to update it.
Attach resume as .pdf, .doc, .docx, .odt, .txt, or .rtf (limit 5MB) or Paste resume

Paste your resume here or Attach resume file