Connect with us icon Connect With Us

Data Engineer

Sorry, we’re not accepting applications for this job right now. But don’t go yet! Explore our site to find more opportunities to join us in transforming the future of health care.


Job Purpose

Individuals in this role are expected to be comfortable working as a programmer and also as a quantitative researcher. The ideal candidate will have a keen interest in the study of healthcare language and data, and a passion for identifying and answering questions that help us build the best products.
The informatics professional will analyze, assess and evaluate the data produced by clinical natural language processing (NLP) systems and recommend improvements to the system. In addition, the candidate will analyze and assess the data needs of projects and recommend the appropriate data and sources to fill those needs. This position is highly collaborative requiring the candidate to interface with several members within a diverse, interdisciplinary team.

• Evaluate the performance of multiple clinical NLP algorithms to help achieve best performance
• Drive the collection of new data and the manipulation and refinement of existing data sources.
• Analyze and interpret the results of data analyses.
• Communicate key findings from experimentation to appropriate groups to help define solutions to problems and/or gaps in our system.
• Develop best practices for instrumentation and experimentation and communicate those to product & engineering teams.
• Lead the implementation of strong theoretical and practical knowledge of analytical techniques including mix and time series modeling, response modeling, experimental design, optimization and techniques.
• Apply state-of-the-art techniques (data mining, machine learning, artificial intelligence, core mathematical-modeling and dynamic processing to data visualization) to extract actionable insights through analysis of large-scale, high-dimensional data.
• Collaborate with subject matter experts, academic partners, and internal/external stakeholders to design systems for data collection, cleaning, statistical analysis, and predictive modeling.
• Provide guidance on data structures and design for reporting, ad-hoc analyses and propensity modeling driving insights around patients, members and care delivery improvement strategies.
• Generate conceptual models, sharing and articulating those theories and quantifying the limitations of implemented models.
• Work with engineering teams on best implementation and use of the data to solve a business problem.
• Work independently on user stories, can own and work on story grooming and execution when needed.
• This position is ultimately responsible to address the organization's need for accurate, timely and thoughtful data analysis work using the resources within the organization.
• Participation in the Informatics group Kanban process, with appropriate attention paid to grooming, prioritization, definition of ready, definition of done.
• Ability to work cooperatively and constructively with many other teams and roles.

Preferred experience:
• Advanced proficiency in analyzing languages, particularly syntactic and semantic analysis.
• Extensive experience solving analytical problems using quantitative approaches.
• Comfortable manipulating and analyzing complex, high-volume, highly dimensional data from varying sources.
• A strong passion for empirical research and for answering hard questions with data.
• A flexible analytic approach that allows for results at varying levels of precision.
• Ability to communicate complex quantitative analysis in a clear, precise, and actionable manner.
• Fluency with at least one scripting language.
• Familiarity with databases and SQL.
• Experience with analysis tools such as R, Matlab, or SAS a plus.
• Hypothesis testing: being able to develop hypothesis and test them with careful experiments
• Machine learning: using preexisting packages and platforms to improve as well as develop algorithms
• Familiarity with and ability to apply descriptive statistics and hypothesis testing
Knowledge of Health Care Finance and Operations is desirable. Prior experience with electronic health records (e.g. EPIC, CERNER, Imaging) or healthcare financial data a plus. Software engineering or other engineering experience a plus. 


Bachelor's Degree in Computer Science or healthcare related field and 5+ years relevant experience or equivalent combination of education and experience required. Must have knowledge of regulatory requirements, and healthcare domain experience. Relational data base design and development. SQL programming fundamentals. Knowledge of Health Care Finance and Operations is desirable. Prior experience with EPIC, CERNER, Imaging or healthcare financial data a must. Scripting, coding or other engineering experience a plus.

Licensure, Certifications, and Clearances:

UPMC is an Equal Opportunity Employer/Disability/Veteran

Location: Pittsburgh, PA, United States
Job ID: 38370340

UPMC is an equal opportunity employer.
Minority / Females / Veterans / Individuals with Disabilities