ABOUT EPISOURCE:
Episource has devoted more than a decade in building solutions for risk adjustment to measure healthcare outcomes. As one of the leading companies in healthcare, we have helped numerous clients optimize their medical records, data, analytics to enable better documentation of care for patients with chronic diseases.
The backbone of our consistent success has been our obsession with data and technology. At Episource, all of our strategic initiatives start with the question - how can data be “deployed”? Our analytics platforms and datalakes ingest huge quantities of data daily, to help our clients deliver services. We have also built our own machine learning and NLP platform to infuse added productivity and efficiency into our workflow. Combined, these build a foundation of tools and practices used by quantitative staff across the company.
What’s our poison you ask? We work with most of the popular frameworks and technologies like Spark, Airflow, Ansible, Terraform, Docker, ELK. For machine learning and NLP, we are big fans of keras, spacy, scikit-learn, pandas and numpy. AWS and serverless platforms help us stitch these together to stay ahead of the curve.
ABOUT THE ROLE:
We’re looking to hire someone to help scale Machine Learning and NLP efforts at Episource. You’ll work with the team that develops the models powering Episource’s product focused on NLP driven medical coding. Some of the problems include improving our ICD code recommendations, clinical named entity recognition, improving patient health, clinical suspecting and information extraction from clinical notes.
This is a role for highly technical data engineers who combine outstanding oral and written communication skills, and the ability to code up prototypes and productionalize using a large range of tools, algorithms, and languages. Most importantly they need to have the ability to autonomously plan and organize their work assignments based on high-level team goals.
You will be responsible for setting an agenda to develop and ship data-driven architectures that positively impact the business, working with partners across the company including operations and engineering. You will use research results to shape strategy for the company and help build a foundation of tools and practices used by quantitative staff across the company.
During the course of a typical day with our team, expect to work on one or more projects around the following;
1. Create and maintain optimal data pipeline architectures for ML
2. Develop a strong API ecosystem for ML pipelines
3. Building CI/CD pipelines for ML deployments using Github Actions, Travis, Terraform and Ansible
4. Responsible to design and develop distributed, high volume, high-velocity multi-threaded event processing systems
5. Knowledge of software engineering best practices across the development lifecycle, coding standards, code reviews, source management, build processes, testing, and operations
6. Deploying data pipelines in production using Infrastructure-as-a-Code platforms
7. Designing scalable implementations of the models developed by our Data Science teams
8. Big data and distributed ML with PySpark on AWS EMR, and more!
BASIC REQUIREMENTS
-
Bachelor’s degree or greater in Computer Science, IT or related fields
-
Minimum of 5 years of experience in cloud, DevOps, MLOps & data projects
-
Strong experience with bash scripting, unix environments and building scalable/distributed systems
-
Experience with automation/configuration management using Ansible, Terraform, or equivalent
-
Very strong experience with AWS and Python
-
Experience building CI/CD systems
-
Experience with containerization technologies like Docker, Kubernetes, ECS, EKS or equivalent
-
Ability to build and manage application and performance monitoring processes