Principal Data Scientist

Optum is a global organization that delivers care, aided by technology to help millions of people live healthier lives. The work you do with our team will directly improve health outcomes by connecting people with the care, pharmacy benefits, data and resources they need to feel their best. Here, you will find a culture guided by inclusion, talented peers, comprehensive benefits and career development opportunities. Come make an impact on the communities we serve as you help us advance health optimization on a global scale. Join us to start** Caring. Connecting. Growing together.**
- Our work area includes development of data science models to identify aberrant billing patterns in healthcare claims data. We are a team of data scientists working on developing, evaluating of advance data science models
- Role requires evaluation of various data science models through advanced statistical techniques and identify improvement opportunities resulting in business impact, creating different metrics for models, and building solid relationships with global analytics teams

**Primary Responsibilities**:

- Leading a team of highly qualified team of data scientists with experience in formulating and solving complex problems
- Oversee development of predictive modeling algorithms using statistical tools, statistical modeling, optimization, algorithm development to synthesize large data sets
- Providing both technical consulting to business leaders at an appropriate level of information encapsulation
- Develop actionable AI, NLP, machine learning solutions and propose recommendations and strategies to solve commercial opportunities in unique ways that return optimal value to our business
- Use a flexible, analytical approach to design, develop, and evaluate predictive and prescriptive models and advanced algorithms that result in optimal value extraction from the data
- Deliver robust and scalable analytic solutions in an automation ready state
- Collaborate with lines of business to understand their analytic needs, contribute to shaping business solutions and communicate results of analytics
- Develop and expand a fledgling applied research program with focus on impact-focused initiatives, rapid prototyping, and obsession with converting applied research into software
- Be a hands-on leader and teach by example by building prototypes using variety of predictive methods while adhering to the AI, ML development cycle (e.g. iterative EDA, prediction specification, feature engineering and model tuning)
- Participate in meetings business stakeholders, data experts, software/platform engineering, physicians to scope R&D use-cases and convert them into scope of work
- Be a thought leader and coach the junior team members in the wide variety of statistical/predictive methods (e.g. DL, VAE, Bayesian nets etc) to attack a given prediction use-case
- Comply with the terms and conditions of the employment contract, company policies and procedures, and any and all directives (such as, but not limited to, transfer and/or re-assignment to different work locations, change in teams and/or work shifts, policies in regards to flexibility of work benefits and/or work environment, alternative work arrangements, and other decisions that may arise due to the changing business environment). The Company may adopt, vary or rescind these policies and directives in its absolute discretion and without any limitation (implied or otherwise) on its ability to do so

**Required Qualifications**:

- PhD/M.Sc./MS College Degree or Higher in operational research, applied mathematics, statistics with a quantitative emphasis from tier I colleges only
- 10+ years of experience conducting statistical, research-minded analysis of variety of data types/forms with aim to utilize this analysis into building or optimizing predictive methods
- 10+ years of deep, hands-on experience in Deep Learning, NLP, AI, machine Learning and Computer Vision applied to the healthcare or other high-stakes domains (direct experience in a cloud environment is highly valued)
- 10+ years advanced programming exposure in SAS or Python including SQL, and good exposure to tool/libraries/forms such as Spark, pandas, scikit family, numpy/scipy, matplotlib, streamlit
- Experience with one or many of these topics such in customer churn, intent prediction, disease/damage progression, anomaly detection, sequence-based models, time-series forecasting or time to event modeling
- Experience in deploying machine learning models in a production setting (logging, monitoring, alerts) in a cloud environment
- Proven experience in understanding complex problems and datasets and driving data testing and strategic testing of ideas to come up with first-class solutions
- Self-drive knowledge accumulation of methods and modeling advances by reading research publications, blogs and attending presentations and webinars
- Proven ability to offer thought leadership at a meta level

**Preferred Qualification**