Data Scientist (NLP)
New York, NY

Job Description

Prognos is an NYC-based healthcare startup whose moonshot is to Eradicate disease so that humanity can fulfill their potential. In order to achieve this goal we have curated the world's largest clinical lab dataset --covering almost 200M patients in the US-- and are currently deploying cutting-edge technology for predicting disease at the earliest possible time.

The Mission of the Data Science team at Prognos is to develop, deploy and maintain AI/ML pipelines within all of Prognos' products, addressing business-relevant problems in close collaboration with Engineering, Clinical and Product teams.

We are looking for a hands on (IC) Senior Data Scientist to join the team, and help us move this mission-critical task forward. This position will have an initial focus of driving our natural language processing (NLP) capabilities forward, then expand into general predictive modeling.

Candidates must have a degree in Statistics/Biostatistics, Computer Science, or a related quantitative field; Masters or higher is preferred. At least 3 years of hands on machine learning (ML) experience required.

Required Skills and Experience

* Strong statistical analysis background with a deep understanding of a variety of ML algorithms and statistical modeling techniques
* Enthusiastic about making sense of unstructured data using NLP or graph-based techniques
* Ability to code a proof of concept in a short period of time (in a programming language of their choice)
* Have at least 2 years of industry experience in NLP or sequence modeling (classic random-field or markovian techniques as well as modern attention-based ones)
* Willingness to stay abreast of and evaluate recent advances in NLP and sequence modeling in general
* Experience with relevant software tools, such as Python, PyTorch, Gensim, Spacy, scikit-learn, statsmodels, and/or others. You'll be free to use whatever tools you feel are appropriate
* Comfortable extracting data using SQL, Apache Spark or other distributed compute engine
* Accustomed to working with GIT and shared codebases
* Extensive data cleaning and textual data manipulation experience
* Strong communication skills. Experience presenting experimental to people who are not Data Scientists
* Ability to collaborate with the team and translate existing research into practical solutions and products
* Ability to build and maintain relationships with various collaborators across the company, and take ownership of data science projects

Preferred Skills and Experience

* Experience with complex, high dimension, sparse time series data
* Experience with PyTorch Geometric, GPyTorch and more specifically PyTorch's NLP ecosystem
* Experience with healthcare data and/or insurance data a plus

Prognos Values & Culture

* Be Collaborative: Always do what is best for the client. Check your ego at the door. We deliver premium value at a premium price. Practice blameless problem solving. Create win/win solutions.
* Be Courageous: Do the right thing, always. Look at the facts and don't assume.
* Be Curious: Think big and start small. Be relentless about improvement. Be predictive. Be curious and always ask why
* Be Enthusiastic: Celebrate success. Be enthusiastic and positive. Let's have fun. Have purpose and believe in the greater good.
* Be Driven: Act with a sense of urgency. Take ownership and honor commitments. Either find a way or make one. Deliver results.
* Be a Superstar: Make quality personal. Deliver remarkable client service. Be better than your previous self. Go above and beyond.
* Our culture guide: http://bit.ly/2ISMzjl

About Prognos

Prognos is a healthcare AI company focused on predicting disease to drive decisions earlier in healthcare in collaboration with payers, Life Sciences and diagnostics companies. The Prognos Registry is the largest source of clinical diagnostics information in 40 disease areas, with over 16B medical records for 185M patients. Prognos has 1000 extensive proprietary and learning clinical algorithms to enable earlier patient identification for enhanced treatment decision-making, risk management and quality improvement. The company is supported by a $42M investment from Safeguard Scientifics, Inc. (NYSE: SFE), Merck Global Health Innovation Fund (GHIF), Cigna (CI), GIS Strategic Ventures, Hikma Ventures, Hermed Capital, and Maywic Select Investments. For more information, visit www.prognos.ai.

Our Mission

To improve health by driving the best actions learned from the world's data

Our Vision

To prevail over disease and empower people everywhere to live life to the fullest

Selected Perks

* Free FreshDirect food, snacks, drinks, etc. delivered to the office weekly
* Flexible work arrangements and unlimited PTO
* Monthly Happy Hours with Leadership
* Some of our benefits include: Health Insurance, Life Insurance, Short Term and Long Term Disability, Dental, Vision, 401k, HSA, FSA, Dependent care flexible spending, commuter benefits, free access to One Medical Group, Gym discounts, flexible work hours and locations, access to the WeWork network, a Health Advocate, Employee Stock Option Plan, and more