Principal Machine Learning Engineer

Key Skills

Amazon EMR, Amazon Simple Storage Service (S3), AWS, AWS Sagemaker, CloudWatch, Data science techniques, Docker, Elasticsearch, Machine learning techniques, Natural Language Processing (NLP), Natural Language Toolkit - NLTK, Project management, PySpark, Python Programming, PyTorch

Job Description

In this role, you will join our growing team of world-class engineers, statisticians, and clinical experts to deploy machine learning algorithms that help automate burdensome administrative clinical practices. You will be tasked with finding the most promising opportunities for impact and then delivering on them. Our machine learning team’s work is focused in the following four areas: information retrieval from unstructured clinical text; predicting clinical findings from structured and unstructured data sources; building intelligent algorithms for ordering work queues; and identifying anomalies, such as behavior change and gaming, in user behavior.

What you will do:

• Perform in-depth analysis of healthcare data coupled with data from product and other sources to independently design, develop, and deliver ML models.
• Build reliable and scalable production machine learning systems.
• Work on feature engineering, statistical analysis, developing novel ML techniques, understanding model performance, and ensuring fit-for-purpose.
• Work cross-functionally across diverse stakeholders, including product managers, statisticians, EHR data specialists and physicians.
• Optimize algorithms, running in real-time, for speed and accuracy.

Your background & requirements:

• Position requires either (i) Master’s degree (or an equivalent foreign degree) in Computer Science, Machine Learning, Mathematics, or a closely related field and six years of professional work experience in the field of machine learning; or (ii) PhD (or an equivalent foreign degree) in Computer Science, Machine Learning, Mathematics, or a closely related field and three years of professional work experience in the field of machine learning.
• Must also have 3 years of experience (which can have been gained concurrently with the primary experience requirement above) working with the following:
• Building and maintaining Natural Language Processing (NLP) models (including usage of techniques such as topic modeling, NER, sentiment analysis, etc.);
• Deploying NLP models into production and optimizing said models for product use;
• Python and relevant libraries such as huggingface, SpaCy, NLTK, and PyTorch;
• AWS tools such as SageMaker, S3, CloudWatch, Lambda, EMR, Athena and ECS; and
• Leading technical projects and/or mentoring junior engineers.

Note: This is a telecommuting position working from home. May reside anywhere in the United States.