Sr. Principal Data Scientist

San Mateo, CA
Technology – Data Science
The Company 
WithMe Health provides a medication guidance solution that replaces legacy Pharmacy Benefit Managers (PBMs) by using modern technology and rich datasets to consistently apply proven science and create individualized experiences for employees and their families. WithMe Health’s solution is unlike any other medication guidance solution in the market today: it is proactive, adaptive, convenient, and engaging. And WithMe Health’s innovative, outcomes-oriented business model aligns interests across the pharmaceutical value chain, optimizing health outcomes while substantially reducing costs for employers. The company was formed in 2018 to address the growing challenges and unmet needs that employers and employees face with legacy PBMs: misaligned business models, frustrating interactions, unknown outcomes, high costs, and a lack of real transparency. Having recently closed a $20 million round of financing from Oak HC/FT, WithMe Health is poised for significant growth while disrupting the $453 billion PBM industry and is looking to build out its team to help achieve this growth. 

The Role 
WithMe Health is looking for a Principal Data Scientist. What you will do As a Principal Data Scientist at WithMe Health, you will contribute to answering core questions such as: What is the future health and healthcare cost for each person? What medications works for whom? What interventions have the greatest likelihood of impact? You will be part of the design, development, and deployment of WithMe Health’s machine learning platform including: feature vector generation, experiment design, model generation, model evaluation. You will collaborate with both data engineers, clinical, and product towards building the models and rule generation that will drive WithMe’s guidance platform. With a strength for working cross functionally, you will leverage your comprehensive understanding of all aspects of the US health care system to create an innovative clinical framework for value and outcomes in the market. 


    • Development and deployment of models across conditions, HCCs, costs, and other outcome variables 
    • Build and develop all necessary data pipelines 
    • Develop and deploy streaming microservices that enrich the raw data with knowledge and models Develop and deploy standard evaluation frameworks 
    • Develop and deploy per member optimization simulations across financial, clinical and experience outcome variables 
    • Contribute to the success of the team with specific experiment and research directions that can take our guidance platform to the next level 
    • Develop predictive and prescriptive models based on descriptive and diagnostic models 

Qualifications and Experience:

    • Strong python skills in building infrastructure and apps 
    • Work experience with distributing Computing: Scala, Spark, HDFS, Cassandra, ElasticSearch Building and developing data pipelines 
    • Leverage public data sources to enhance machine learning 
    • Train/update/version/maintain production machine learning systems 
    • Python experience: including pandas, numpy, scipy, sklearn 
    • ML Platforms: Tensorflow and others 
    • Machine learning experience: DeepLearning, Random Forests, built Lasso regression, vector embeddings, and more 
    • Understanding of metrics like precision/recall curves, ROC and more 
    • Handle large volumes of heterogeneous medical data 
    • Understanding of medical informatics coding systems such as (NDC, RxNorm, ICD9/10, CPT/HCPCS, LOINC, SNOMED-CT, FHIR/HL7) 
    • Deep professional experience integrating data from various clinical systems like EHR, pharmacy, Lab information systems and claims 
    • Building and designing feature vectors, application of multple machine learning architectures such as deep learning (MPL, RSTM, etc), Random Forest, Bayesian, Regression, ..., model validation ROC and Precision/Recall, Esmemble models, multi-Ranking, Embeddings, ... 
    • Excellent communication skills with clear emphasis on collaboration 
    • Working version of the feature augmentation pipeline (v1.0) 
    • Prototype predictive models on various tasks, and having finished with initial tests, confirmed by medical experts 
    • Documenting the process, things that worked and didn't work, structuring the company's AI knowledge 
    • Assisting hiring more AI talents, coaching/mentoring them, and maybe helping setting up their OKRs and concretizing deliverables and timelines 
    • Have an entrepreneurial spirit and be inspiring and motivate others 
    • Be able to be strategic while getting into the details
    • Experience in high concurrency distributed platforms and applied mathematics 


    • Ph.D/MS or 7+ years of experience 
    • M.S. or Ph.D. degree in Computer Science or related fields 
There are many reasons to come work for us but we’ll just list a few: 
Highly competitive pay 
100% employer-paid health coverage 
401(k) plan eligible day 1 
Medical memberships 
Paid life insurance 
8 weeks’ parental leave for primary caregiver 
Flex spending 
Results-only work environment 
Generous vacation policy 

What does all that mean? It means we want you to be successful and fulfilled; to be happy and to grow. We are trying hard to be one of the best places to work and we pride ourselves on doing more for our people. We have some amazing people here and are excited to talk to you more about joining us. Are you ready? 

WithMe is committed to providing reasonable accommodations for qualified individuals with disabilities and disabled veterans in our job application procedures.