Applied Data Scientist
At Lumere, we are clinicians, researchers, engineers, analysts, marketers, and strategic thought leaders focused on one mission: helping hospital leaders and physicians deliver the highest quality, most efficient care by uncovering and eliminating unwarranted care variation and unnecessary costs – specifically related to device and drug selection and utilization.
Our vanguard approach? Partnering with health systems to ensure that care delivery choices are always backed by data and guided by evidence, drug and device costs are justified by clinical outcomes, and doctors and hospital leaders have access to the right insights and analytics to make the best care decisions for every patient.
What you will be doing:
As an Applied Data Scientist at Lumere you’re responsible for building and managing the predictive models that power our product and business. You’re a part of our Data Engineering team, where internal automation and data scale problems are daily challenges, but you’ll also work directly with Product Managers to conceptualize and develop new applications of our data that further our evidence-based mission to improve healthcare.
The successful candidate will be a self-motivated individual with excellent communication and technical skills. You'll have a proven track record of delivering robust and actionable models to production. You will be experienced with a wide variety of data science techniques, tools and platforms, able to articulate the benefits of each and appropriately balance speed of delivery with accuracy and maintainability.
- Collaboration with product management and engineering to integrate new prediction models into our software solutions
- Improving the speed and accuracy of our existing models and the infrastructure that underlies it
- Exploratory work to help the team understand what conclusions can be drawn from new data
- Working with the rest of our Data Engineering and Data Ops team members to integrate your output into the daily workflow of the company
- 4+ years experience in quantitative analysis; 2+ years of data science, predictive modeling, or applied statistics experience; Masters or PhD in a quantitative field preferred
- Strong product instincts and a demonstrated ability to learn the domain at hand, communicate, and work cross-functionally
- Extensive experience with a wide variety of different algorithms and an ability to communicate effectively about the trade offs between approaches
- Experience with our existing stack (R/Python, scikit-learn, AWS)
- Exposure to natural language processing techniques and distributed compute technologies such as Apache Spark or Hadoop considered a plus
- Strong SQL proficiency and a working knowledge of both relational database and warehousing technologies (Postgres, Redshift) as well as database performance considerations
- Working knowledge of professional software development tools and processes (Scrum, git, etc.)
- Organized, highly motivated individual with excellent collaboration, project management and problem-solving skills