Data Scientist

February 23

Sword Health

WebsiteLinkedInAll Job Openings

Sword Health is the world’s fastest growing virtual MSK care provider, on a mission to free two billion people from pain

Digital Health • medical devices • machine learning • Artificial Intelligence • physical therapy

201 - 500

Description

• Lead data science projects to design, prototype and test novel clinical and digital interventions to understand member musculoskeletal health needs and behavioral tendencies. Leverage advanced programming and large datasets towards those ends, including claims, engagement data, structured and unstructured clinical notes, focused on developing domain expertise in digital health and musculoskeletal care. Work and collaborate with internal stakeholders (clinical affairs, analytics, marketing, clinical operations, growth) to develop strategies and data science products to solve real world problems. Work alongside data engineers and product managers to deploy designed and well-tested ML models into practice, helping design appropriate frameworks to test and monitor ongoing model performance (e.g. model drift, data drift) and evaluate true downstream impact on care and operations. Provide methodological, statistical, design and analytical guidance for new and ongoing operations and applied research projects. Partner with business groups in the company to identify opportunities to deploy bespoke models and create additional models to answer key questions about member behavior.

Requirements

• Minimum 1 year working on multiple projects involving large data sets, including training, testing, and deploying machine learning algorithms into cloud environments, and specific experience with deep learning required (e.g., RNNs, CNNs, etc). Prior experience translating data findings and data science concepts for lay audiences, including the production of presentations for senior-level audiences (excellent verbal and written communication skills) also required. Strong understanding of data science and statistical concepts, computer programming, and their applications to real-world data required. Specifically, strong programming proficiency (e.g., Python, TensorFlow, PyTorch, R, Spark, SQL). Prior experience with code repositories such as git or equivalent is also required. Ability to engage with existing ideas and champion new ones that add value to the organization. Ability to analyze problems, issues and opportunities systematically and logically to make decisions that support the mission, vision, values and goals of the organization. Understand the biases that data collection and sampling can introduce, and know how to design and implement methods that adjust for those biases when possible. Love to discover how things work through the lens of data, are not intimidated by “messy” data sets, and enjoy communicating your insights to broad audiences. Ability to communicate data science concepts to non-technical stakeholders. Ability to deliver and ship results iteratively on a regular basis to executive stakeholders and produce pipeline-ready code and documentation. Take initiative in pushing the team’s thoughts and ideas and exploring novel applications of machine learning techniques to solve problems. Don’t just follow objectives but try to push the boundaries of what is possible in solving for thorny, complex issues as a thought leader within the team.

Benefits

• Comprehensive health, dental and vision insurance • Equity Shares • 401(k) • Discretionary PTO Plan • Parental leave • Flexible working hours • Remote-first Company • Internet Stipend for remote working • Paid Company Holidays • Free Digital Therapist for you and your family • Meal Allowance • Remote Work Allowance • Work from home • Unlimited Vacation • Snacks and Beverages • English Class • Unlimited access to Coursera Learning Platform