Principal Data Scientist - NLP/AI/ML - Remote

Georgia Work at Home, United States

The Cigna Group

Discover The Cigna Group, a global health company committed to improve the health and vitality of those we serve.

View all jobs at The Cigna Group

Apply now Apply later

OVERVIEW:

A career within Forsyth Health’s Product team will provide you with the opportunity to help Pharma/Life Science organizations uncover patient and market insights. At Forsyth Health, we focus on a collection of data management, business intelligence, advanced analytics and data science capabilities to support various functions within these organizations to meet their business needs around market access and patient support programs.

How you'll make a difference:

The Principal Data Scientist role is a key role to the enterprise and will be leading a highly complex and growing area within the health care data and product development space. As a strong individual contributor, with a potential for taking on supervisory responsibilities, the role will lead product development efforts using NLP and machine learning technologies and workflows.  The role will help design Forsyth’s data product features that utilize unstructured clinical and other text data to enable research within the commercial Pharma Analytics space. Responsibilities include mining unstructured data, help develop healthcare domain-specific ontologies, assist in development of use cases and data curation models and algorithms that help bring “research-ready” datasets to market. This role will work closely with the internal Technology, Analytics, and Client Services teams to support and showcase Forsyth data capabilities with both existing and potential clients. 

Role Summary:

The Principal Data Scientist position is an opportunity for a Data Scientist/NLP Engineer to establish NLP and ML based development workflows and meaningfully impact the design and development of the Forsyth Enterprise Data Model. The job responsibilities include, but are not limited to the following:

  • Develop and implement NLP models and algorithms, such as, text classification, sentiment analysis, named entity recognition, etc. with the goal of adding clinical data attributes, denial reason details and other variables to the Forsyth data model.

  • Design, build and optimize NLP pipelines.

  • Design and build training datasets and associated workflows as needed, including workflows for validating NLP/ML-derived outputs.

  • Collaborate with data engineers to deploy NLP models into production environments.

  • Work with other cross-functional teams to gather and refine requirements for mining text and design resulting variables

  • Efficiently query multiple data types (medical and pharmacy claims, EMR, lab, chargemaster) as needed to gain a deeper understanding of patient / clinical activity from Forsyth data to validate and further refine NLP/ML models and output.

  • Create and maintain technical documentation for NLP models and algorithms.

  • Work with Client Solutions in understanding client needs and/or providing training and guidance to clients and help derive value out of NLP-sourced variables. 

  • Project management and prioritization – support multiple projects per Product roadmap and work with Client Solutions, Data and Analytics teams to manage multiple initiatives and negotiate timelines/priorities with stakeholders. 

  • Lead NLP function for Forsyth including evaluating resource needs, expanding NLP team at the appropriate time, recruiting/hiring, establishing and managing team responsibilities and prioritizing work against Product roadmap.

Qualifications:

  • 7-10 years of experience in data science and software engineering, with at least 5 years in solving complex business problems using NLP and ML models, data tools, and analytical processes.  Bachelor’s degree in a related field preferred.

  • At least 3-5 years in healthcare data space.

  • Excellent programming skills in languages like Python, SQL, Pyspark, Java, C++, etc.

  • Advanced knowledge in ML tools such as PyTorch, Scikit-learn, LLMs, etc.

  • Deep understanding of NLP techniques, including text representation, semantic extraction and data structures.

  • Experience with cloud computing platforms and development tools such as Azure Databricks, Azure Data Lake, AWS, etc.

  • Demonstrated attention to detail, ability to compile and analyze information, ensure data integrity, and provide resolutions or recommendations for improving operational processes.

  • Excellent communication and presentation skills.

  • Desired: experience applying real-world data to specific healthcare and life sciences-related research questions and use cases.


If you will be working at home occasionally or permanently, the internet connection must be obtained through a cable broadband or fiber optic internet service provider with speeds of at least 10Mbps download/5Mbps upload.

For this position, we anticipate offering an annual salary of 147,200 - 245,300 USD / yearly, depending on relevant factors, including experience and geographic location.

This role is also anticipated to be eligible to participate in an annual bonus and long term incentive plan.

We want you to be healthy, balanced, and feel secure. That’s why you’ll enjoy a comprehensive range of benefits, with a focus on supporting your whole health. Starting on day one of your employment, you’ll be offered several health-related benefits including medical, vision, dental, and well-being and behavioral health programs. We also offer 401(k) with company match, company paid life insurance, tuition reimbursement, a minimum of 18 days of paid time off per year and paid holidays. For more details on our employee benefits programs, visit Life at Cigna.

About Evernorth Health Services

Evernorth Health Services, a division of The Cigna Group, creates pharmacy, care and benefit solutions to improve health and increase vitality. We relentlessly innovate to make the prediction, prevention and treatment of illness and disease more accessible to millions of people. Join us in driving growth and improving lives.

Qualified applicants will be considered without regard to race, color, age, disability, sex, childbirth (including pregnancy) or related medical conditions including but not limited to lactation, sexual orientation, gender identity or expression, veteran or military status, religion, national origin, ancestry, marital or familial status, genetic information, status with regard to public assistance, citizenship status or any other characteristic protected by applicable equal employment opportunity laws.

If you require reasonable accommodation in completing the online application process, please email: SeeYourself@cigna.com for support. Do not email SeeYourself@cigna.com for an update on your application or to provide your resume as you will not receive a response.

Cigna has a tobacco-free policy and reserves the right not to hire tobacco/nicotine users in states where that is legally permissible. Candidates in such states who use tobacco/nicotine will not be considered for employment unless they enter a qualifying smoking cessation program prior to the start of their employment. These states include: Alabama, Alaska, Arizona, Arkansas, Delaware, Florida, Georgia, Hawaii, Idaho, Iowa, Kansas, Maryland, Massachusetts, Michigan, Nebraska, Ohio, Pennsylvania, Texas, Utah, Vermont, and Washington State.

Qualified applicants with criminal histories will be considered for employment in a manner consistent with all federal, state and local ordinances.

Apply now Apply later

Tags: AWS Azure Business Intelligence Classification Databricks Data management Engineering Java LLMs Machine Learning ML models NLP Pharma Pipelines PySpark Python PyTorch Research Scikit-learn SQL Unstructured data

Perks/benefits: 401(k) matching Career development Health care Insurance Salary bonus

Regions: Remote/Anywhere North America
Country: United States

More jobs like this