Grand Rounds is a new kind of healthcare company. Founded in 2011, the company is on a mission to raise the standard of healthcare for everyone, everywhere. The Grand Rounds team goes above and beyond to connect and guide people to the highest quality healthcare available for themselves and their loved ones. Grand Rounds creates products and services that give people the best possible healthcare experience. Named a 2019 Best Place to Work by Glassdoor and Rock Health’s 2018 Fastest Growing Company, Grand Rounds works with inspiring employers and doctors to empower them to be the change agents we need to make our shared vision a reality.

Machine Learning Engineers and Data Scientists at Grand Rounds work on problems that are core to the company’s mission. Major challenges include developing systems and models to identify the highest quality doctors in the country as well as methodologies to uncover the subtle differences between each physician’s clinical expertise. Additionally, patient-level modeling allows us to understand the specific healthcare needs of every person. With a high fidelity understanding of both patients and physicians we are able to match patients to both appropriate and high quality care and understand the health of our patient populations. Our growing group of machine learning engineers sit on the Data Science team while also working closely with other data infrastructure focused teams, including Data Engineering and Platform. Machine Learning Engineering is tasked with building out search and analytics platforms powered extensively by machine learning technologies. 

Example Projects Include:

• Data Science platform and infrastructure. You will play a critical role building tools and infrastructure to support Grand Rounds’ vision to be a personal healthcare assistant to our members. A key focus area will involve reshaping and extending our brand new Data Science platform. This multipurpose Spark-based ecosystem will enrich our view of providers and patients through machine learning driven inference and population health statistics. The tooling developed will support a combination of modeling, experimentation, and measurement capabilities to build a rich algorithmic understanding of the clinical needs of our members, the value and efficacy of GR interventions and the propensities for utilization. You will work closely with our Data Engineering and Platform teams,  as well as data scientists, to ensure robust modeling and data delivery systems that operate at the required scale and velocity. 


• Structuring data from medical text. Grand Rounds provides more types of care to a broader pool of members than ever before, and we are expanding our ability to process text generated by these encounters to yield structured data. This effort is to help our Care Team scale and generate new insights on our patient population. You will apply a mixture of pipeline expertise, natural language processing, data warehousing, and healthcare domain knowledge to accurately identify and surface information from medical notes. 


• Building modules for our “Match Engine” ecosystem. This collection of services powers our provider matching backend in terms of distributed runtime and deployment services.  As data scientists across our team are constantly developing new models and features that will help patients immediately, we aim to publish these into our own integrated platform.  You will help solidify, grow, and lead the evolution of the end-to-end systems architecture. As a user-facing real-time prediction environment, we take seriously the notions of instrumentation, optimization of both models and orchestration code, as well as the construction and integration of online and offline experimentation frameworks.

Qualifications:

• Excellent verbal communications, including the ability to clearly and concisely articulate complex concepts to both technical and non-technical collaborators
• BS with 8+ years or MS with 6+ years or PhD with 3+ years of experience. Degree(s) should be in a technical discipline such as Computer Science, Engineering, Statistics, Physics, Math, quantitative social science
• Previous experience in machine learning, and statistics fundamentals
• Production engineering experience is highly desired including previous experience developing and maintaining high-availability search and/or machine learning services.
• Experience as a tech lead for these types of projects is preferred
• Experience with distributed systems componentry including Kubernetes or other container management, SQL and NoSQL databases, caching layers (Redis, Memcached), compute in Spark or Hadoop, queueing (Kafka, Kinesis, SNS), cloud-based databases (BigQuery, Athena, Redshift)
• Experience with workflow management solutions such as Prefect, Airflow, Azkaban, or Luigi and scalable ETL in batch and stream processing workloads in Spark, Hadoop
• Required: SQL, Python, linux shell scriptingBonus Points: Scala, Java, Go, or Ruby
• Experience with production ready machine learning packages such as scikit-learn, TensorFlow, PyTorch, SparkML and/or natural language frameworks such as SpaCy or NLTK.
• Frequent user of cloud computing platforms such as Amazon Web Services and Google Cloud Platform
• Double Bonus Points: previous work on medical applications and/or with claims data