Data Science

Data Scientist, AI & Data Insights (San Francisco)

In this role, you will work closely with our commercial partners to deliver insights from real world medical data. You must have an appetite for problem solving, an aptitude for framing scientific questions, and a history of delivering high-quality code.

Responsibilities

• Gather requirements for internal and external research projects and products
• Collaborate on multi-disciplinary teams to implement technical solutions for commercial research projects and client-facing products
• Write and maintain code automating data curation tasks on a big data scale
• Create curated datasets and synthetic tables from raw structured and unstructured data for customer deliverables
• Create, maintain, and use scripts segmenting patient populations for analysis
• Define, apply, and interpret machine learning models that describe patient journeys

Requirements

• 5+ years developing and using advanced analytical tools and code*
• 2+ years experience working directly with external stakeholders on data science problems*
• 2+ years implementing production-grade pyspark or python and SQL code
• Proven experience working on cross-functional teams
• History of implementing data curation and ETL tasks
• Good understanding of modern data engineering architectures
• Application-oriented machine learning modeling

Bonus

• Familiarity with medical data types and nomenclatures (e.g., ICD-10, CPT, RxNorm)
• Experience with unstructured data, NLP methods
• Familiarity with clinical research, electronic health record systems/data
• Experience with Spark, AWS

* 3-5 years experience considered if strong experience with at least two of the following bonus skills: healthcare/clinical trial data, ETL, unstructured text analytics, application-oriented regression/boosted tree ML models, big data technologies

Clinical Data Scientist (San Francisco)

Verana Health is looking for an experienced data scientist with a background in health data analytics to help us with data interpretation, cleaning, modeling, queries, and visualization.

Responsibilities

• Work closely with the clinical and technology teams to translate clinical investigation questions into detailed data analytics requirements.
• Implement retrospective clinical studies to generate RWE insights and to answer customer questions.
• Organize clinical data relationships to create a data model and classification hierarchy.
• Examine physician notes and design a model to transform and extract structured data.
• Design visualization reports to represent data analytics results in a meaningful way.

Qualifications

• Strong familiarity with health data analytics tools, especially SQL, Python, Pandas.
• Experience with health data modeling, curation and bio-statistics.
• Familiarity with clinical data sets and coding systems such as ICD, CPT and RxNorm.
• Familiarity with pharmaceutical company business processes, including clinical trials, new drug introduction and clinical operations.
• Ability to work effectively with cross-functional business and technical teams.
• Have excellent drafting, negotiation and very clear communication skills.
• Ability to prioritize and manage multiple projects.
• Ability to manage multiple projects and priorities and attention to detail.

Data Quality Scientist (San Francisco)

As a Data Scientist, you will analyze and interpret complex data and develop data quality algorithms for building high quality data pipelines. The ideal candidate is an experienced data scientist with in-depth programming knowledge (SQL/SAS/R/Python). The Data Scientist will develop operational models, perform data optimizations, create synthetic data tables, perform normalizations, data mining, statistical analyses and data visualizations using Tableau.

Responsibilities

• Detect suboptimal data fields in the data pipeline & platform architecture.
• Research and develop operational models for data quality algorithms.
• Incorporate data quality algorithms into the data pipeline.
• Develop specific data quality scoring for clear determination of business, research and regulatory graded data.
• Perform data quality assurance of all products and data modules in development.
• Collaborate with product, commercial and engineering teams to devise possible solutions.
• Inform leadership of quality-related impacts to commercial business engagements.
• Optimize data delivery, re-design infrastructure for greater traceability, accuracy and completeness.
• Work on fast iteration cycles and tight deadlines using an agile methodology.

Qualifications

• Must have a Bachelor's Degree in Computer Science, Statistics, Applied Math or related field.
• Must have 5+ years experience coding in SQL or Python.
• Expertise with Big Data technologies on AWS, i.e. EMR, Spark.
• Must have 5+ years experience analyzing claims data, healthcare data or experience with clinical research.
• Must have 5+ years experience with various data structures and common methods of data transformation.
• Huge plus with experience with detection of data quality in large scale data.
• Prior Ophthalmology or Neurology experience a plus.
• Excellent written and oral communication skills.
• Ability to set and manage priorities judiciously.
• Ability to articulate ideas to both technical and non-technical audiences. Exceptionally self-motivated and directed.
• Superior analytical, evaluative, and problem-solving abilities.