Summary
Are you wicked smart? Are you a tinkerer at heart who likes to work on the cutting edge and push the bounds of what is possible? The Weil Institute for Critical Care Research and Innovation, within Michigan Medicine?s Department of Emergency Medicine, is in search of a Senior Machine Learning Engineer to join our DataOps team to help build next-generation tooling, using industry best practices, to develop real-time data pipelines, integrate machine learning models into University of Michigan?s EHR system, and monitor the performance of our predictive analytics.

This position offers a unique opportunity to work hand-in-hand with our Machine Learning Specialists and clinical collaborators, to help them get the data they need to build their models and to get those models into a production environment and into the hands of clinicians. Unlike traditional research teams, the Weil Institute is focused on operating like a startup and getting products to market in order to ensure that our work can benefit patients sooner rather than later.

The DataOps team provides two key services for the Weil Institute:

Finding, cleaning, and delivering data to Data Scientists so they can build their models
Providing an environment to deploy and host models to be used by clinicians
As a member of the DataOps team, you will be responsible for managing data pipelines for large sets of PHI data including data extraction, transformation, cataloging, monitoring, integrity, administration, and security. These sets of data include structured EHR data, waveforms from bedside monitors, radiological images, clinician notes (NLP), ventilator data, as well as all supporting data sets and any future data sets that may be required. Additionally, you will be working collaboratively with other members of the team to build out frameworks and infrastructure to automate and deploy our models into production environments.

Success in this role requires an ambitious and self-motivated individual capable of identifying areas for improvement, designing solutions, and prioritizing work to ensure that we are meeting our goals. This often involves learning new languages, technologies, and skills in order to ensure that we are delivering the best solutions possible. An inquisitive individual with a strong desire for continuous improvement and always taking the next best step is a strong fit at the Weil Institute.

Who We Are
The Weil Institute Overview

The Weil Institute at the University of Michigan is one of the world?s first comprehensive research enterprises devoted to transforming critical care medicine by accelerating science and moving it from bench to bedside. To do this, the Weil Institute brings together integrative teams of world-class U-M scientists, clinicians, and engineers with industry partners and funding sources to develop and deploy cutting-edge solutions that elevate the care, outcomes, and quality of life of critically ill and injured patients and their families.

Responsibilities*
Manage and administer the design and development of data structures and data extracts to support comprehensive data collection and extraction for complex analysis
"Go To" resource for our most complex technical problems
Build and improve tooling to automate data pulls
Transform ad-hoc data pulls into real-time pipelines
Design and develop applications to deploy real time analytics
Administer infrastructure to support data and applications
Implement monitoring solutions to ensure data integrity and pipelines are operational
Build and integrate data cataloging into pipelines to ensure data security and enable future automation
Communicate clearly and consult with our multi-disciplinary team of scientists, developers, and clinicians
Actively participating in discussions and decisions made by the team. We rely on each other and hold each other accountable
Determine and document requirements
Estimate and adjust stories and sprints
Investigate new technologies and share with the team
Required Qualifications*
The Weil Institute Machine Learning Engineer Senior must have a bachelor's degree in Engineering, Computer Science, Applied Mathematics, Statistics, or Data Analytics or equivalent experience with a minimum of 7 years of increasingly complex business programming experience in a data-driven business environment.

In additional to the above requirements, candidates must also possess the following qualifications:

Proficiency using relevant tools (Python, SQL, Docker)
Experience working in a Unix environment
Familiarity with ML concepts (supervised learning and deep learning)
Knowledge of commonly used software development concepts such as unit testing, git, publish-subscribe architecture, CI/CD, and REST interfaces
Ability to manage multiple projects and assignments with a high level of autonomy and accountability for results
Willingness to learn and quickly adjust to new tools and systems
Capable of converting ambiguous problem statements into concrete project requirements
Excellent verbal and written communication skills including the ability to communicate effectively and professionally with colleagues and stakeholders. Ability to understand and explain technical concepts to non-technical stakeholders
Desired Qualifications*
Familiarity with Kubernetes
Familiarity with RabbitMQ
Familiarity or experience with commonly used data science packages including numpy, pandas, scikit-learn, and tensorflow.
Experience working with big data
Experience developing CI/CD pipelines
Experience working with PHI
Epic certification for working in Clarity