Principal Data Scientist, Search – Telecommute

Key Skills

Java Programming, Risk Analytics, Python Programming, SQL, Machine learning techniques, Deep Learning, Data Modeling, Natural Language Processing (NLP), PyTorch, TensorFlow, Algorithms, PySpark

Job Description

Combine two of the fastest-growing fields on the planet with a culture of performance, collaboration and opportunity and this is what you get. Leading edge technology in an industry that's improving the lives of millions. Here, innovation isn't about another gadget, it's about making health care data available wherever and whenever people need it, safely and reliably. There's no room for error. Join us and start doing your life's best work.(sm)

The Unified Search Team at Optum is working to bring industry-leading search technology and user experiences to tens of millions of healthcare consumers and providers. We are looking for a Data Scientist to collaborate with teams and lines of business across the Optum/United Healthcare enterprise to integrate their data into the expanding Unified Search Platform. Reporting to the the VP of Engineering, they will partner closely with Engineering, Platform and Product teams and collaborate with numerous stakeholders across the business.

We are forming a geographically distributed but cohesive and high-performing team of inquiring minds; we plan our teamwork around flexible schedules and other personal needs. You will be part of a group of innovators who will help drive the change for healthcare consumers.

We are looking for a data scientist who worked or is interested in working on search (ranking and relevance) projects related to healthcare (benefits, claims, providers, clinical content, etc.). This individual should be able to take the lead for one or more of our verticals, mainly concentrating on algorithms and their implementations, working with our platform engineers. We expect you to contribute to our IP with interesting ideas around search relevance. You will contribute to the design of our search data platform, collaborate with other platform leaders to create efficient solutions and deliver state-of-art production systems that are easy to maintain.

You’ll enjoy the flexibility to telecommute* from anywhere within the U.S. as you take on some tough challenges.

Primary Responsibilities:

• Apply advanced statistical and predictive modeling techniques to data related to the optimization of healthcare and digital experiences
• Propose innovative ways to look at problems using data mining, statistical analysis and machine learning
• Communicate findings, verbally and visually, to business partners and clients
• Seek out new data sources and verify the integrity of data that fill gaps and improve models
• Support business needs around analytics, predictive modeling, and business intelligence
• Collaborate effectively with internal clients, transforming their needs into data science use cases
• Provide ongoing tracking and monitoring of the performance of statistical models and recommend ongoing improvements to methods and algorithms

An ideal candidate will have the following:

• Excellent written and oral skills
• Excellent analytical skills; attention to detail, and documentation
• An interest in working with complex data; an interest in building new mechanisms for different domains
• Leading/mentoring junior engineers

You’ll be rewarded and recognized for your performance in an environment that will challenge you and give you clear direction on what it takes to succeed in your role as well as provide development for other roles you may be interested in.

Required Qualifications:

• Master’s degree in computer science, applied mathematics, (bio) statistics, applied statistics, economics, or similar quantitative fields of study
• Hands-on experience in developing analytics with machine learning, deep learning, NLP, and/or other related modeling techniques
• Skilled in python, TensorFlow, PyTorch and/or PySpark
• Ability to turn state-of-art research into production-level codes

Preferred Qualifications:

• Ph.D. degree in computer science, applied mathematics, (bio) statistics, applied statistics, economics, or similar quantitative fields of study
• Experience in developing and deploying models related to a recommender system, NLP, and time series forecasting
• Experience in developing algorithms for financial forecasting (e.g. credit risk, demand, and supply prediction), search engines (e.g. name entity recognition, intent classification, spell correction, autocompletion), cold-start recommendation, semi-supervised learning (e.g. positive unlabeled learning)
• Solid analytical and problem-solving skills
• Ability to translate business needs and requirements into technical solutions