Senior Data Scientist

Overview

Cotiviti is looking for an industry leading Senior Data Scientist focused on machine learning solutions to join a revolution in Healthcare Technology and build value-oriented, production level machine learning solutions. This role is not for the research-oriented data scientist but rather should be of interest to those that want to apply their knowledge and experience to real world problems and seek to utilize Artificial Intelligence and Machine Learning to reduce the cost of healthcare and improve health quality and outcomes.  Cotiviti’s Artificial Intelligence Group consists of data scientists, engineers and data analysts dedicated to developing and implementing robust, scalable, value-based solutions on our proprietary machine learning platform that uses a blend of best-in-class vendor solutions, together with custom built capabilities where gaps in the market exist.   With access to a dedicated Hadoop based multi-node cluster the team can work with a vast amount of structured and unstructured data including claims, membership, physician demographics, medical records, and others to begin to solve some of the most pressing healthcare issues of our time.  A Senior Data Scientist at Cotiviti will be given the opportunity to work directly with a team of healthcare professionals including analysts, clinicians, coding specialists, auditors, and innovators to set aggressive goals and execute on them with the team. This is for an ambitious technologist with the guts, flexibility, and personal drive to succeed in a dynamic environment where the individual is judged based on their direct impact to business outcomes. 

Responsibilities

• Work with data scientists, data science management, business operations, and product management to assess the potential value and risks associated with business problems that have the potential to be solved using machine learning and artificial intelligence techniques. 
• Develop an exploratory data analysis approach with your teams to verify the initial hypothesis associated with potential Artificial Intelligence/Machine Learning use cases. 
• Once verified, develop in depth EDA to create models that meet or exceed the thresholds required to deliver on the use case. 
• Develop the requirements for features required in your final model and interact with the feature library team to get your features built into the library. 
• Document your approach, thinking and results in standard approaches to allow other data scientists to collaborate with your work. 
• Prepare your final trained model using features within the feature library and develop a validation test set for QA. 
• Work with production operations to deploy your model into production and support them in monitoring model performance. 
• Participate in other data science teams collaborating with your peers to support their projects. 
• Participate in knowledge sharing sessions to bring new insights and technologies to the team. 
• Participate in design sessions to continuously develop and improve the Cotiviti machine learning platform. 

This job description is intended to describe the general nature and level of work being performed and is not to be construed as an exhaustive list of responsibilities, duties and skills required. This job description does not constitute an employment agreement and is subject to change as the needs of Cotiviti and requirements of the job change. 

Qualifications

• MS or PhD. Degree in relevant discipline (Mathematics, Statistics, Computer Science, Engineering or Health Sciences) or equivalent
• 5+ years of experience in advanced analytics and applied machine learning solutions. 
• 5+ years of experience in working in Big Data environments, specifically Hadoop.
• History of mentoring data scientists.  
• 5+ years of experience developing machine learning models from novel datasets created in an exploratory data analysis environment then working with others to develop production ready versions of the models that are deployed within operational environments, tracking model impact post deployment, and versioning models appropriately. 
• 5+ years of experience with SQL, ability to write SQL queries to efficiently extract data from SQL Server/Oracle and Hive/Impala. 
• 5+ years of experience using Scala, Python, or R programming languages.  
• 5+ years of experience using Spark framework.  
• 5+ years of experience using machine learning frameworks such as TensorFlow, Scikit-learn, etc. 
• Applied Machine Learning: Application of a variety of machine learning techniques to increase identification of payment integrity issues for our clients, reduce the cost of auditing processes, or increase the quality of care and outcomes for our client’s members.  Must have impl