Who are we?
🫀Vital builds software for care teams and patients, with a focus on the Emergency Room experience. We use machine learning to reduce length of stay, increase provider productivity, and improve patient satisfaction. Vital curates a better healthcare experience for patients and practitioners alike, saving millions of lives in the process.
💡 We provide hospitals with a modern UI and AI layer, which we are able to deploy within a matter of days.
🏥 There are more than 140 million visits to the ER every year in the US. Our mission is to improve the healthcare experience for these patients.
Who are you?
We are looking for a Senior Data Scientist, specializing in NLP, to join our Data Science team at Vital, reporting directly to the VP of Data Science.
You will be joining a small team tasked with the development and ownership of machine learning algorithms which lie at the heart of the Vital product. In particular, your work will focus on leveraging our rich sources of natural language data to improve and create ML-driven products for the application. Making sense of diagnoses, doctors' notes, patient surveys, etc. is pivotal for Vital to be able to deliver effective and personalized healthcare experiences to our patients and providers. Machine learning is essential to the unique value that Vital provides, and your contributions to these systems are crucial to the success of our company!
We are looking for a candidate who is excited to be confronted with new challenges each day. The role comes with significant autonomy, and involves responding to the changing requirements of an early-stage startup. We want you to have opinions, take ownership, and feel that your work has a significant impact on a company which you partly own.
What will you be doing?
- Development and ownership of NLP algorithms which leverage text data to solve healthcare problems
- Working with and improving on our in-house ML platform to train and deploy models
- Forming modeling hypothesis and validating them with experiments and exploratory analyses
- Collaborating with other Data Scientists on their algorithms and analyses
- Writing white papers about your research findings and submitting them to journals and conferences
- Attending and presenting papers at relevant ML conferences when appropriate
- Collaborating with our backend team in order to deliver ML predictions to production
Why work at Vital?
- We’re working on problems which have a real impact on people’s lives. When we succeed, patients get better care.
- Diversity, inclusion, and respect are important to us. Every team member must abide by our shared code of conduct.
- Every team member at Vital gets to share in our success in the form of stock options.
- We provide unlimited PTO for our team, ensuring you can take vacations as you need.
- We provide paid leave for new parents.
- We provide health insurance, and pay all the premiums.
- We have teams in NYC, Atlanta, and Denver, and are happy for you to work anywhere in the US
Requirements
Need to have…
- Bachelor’s Degree in a STEM subject
- Masters/PhD degree in NLP or 3+ years of industry experience in NLP
- 2+ years of experience with production ML systems and platforms
- 2+ years of software development experience in Python
- Experience with Pandas and NumPy
- Experience with PyTorch, TensorFlow, JAX, MXNet, or another deep learning framework
- Experience with UNIX-like environments
- Experience developing NLP algorithms and deploying them in production (i.e. customer-facing)
- Experience with modern software practices including automated testing and continuous delivery
- An ownership mentality, and the desire to take on heterogeneous challenges
NOTE: The hours for this role overlap with our team in New Zealand. Specifically, we need you to be online from 9-11am New Zealand time. Of course, we’re happy for you to start your day later in order to accommodate.
Nice to have…
Some additional skills which we’d find useful if you have them, but should not affect your decision to apply:
- Experience with AWS managed services for ML: SageMaker, Redshift, DynamoDB, Lambda, and Glue
- Experience with MapReduce frameworks such as: Spark, Scalding, Beam, Scio, Crunch, Pig, etc
- Experience with big data querying tools such as: Redshift, BigQuery, Hive, Presto, Mode, etc
- Experience with big data systems: Hadoop, Dataproc, Dataflow, EMR, Databricks, etc
- Experience with No-SQL data bases: DynamoDB, BigTable, Cassandra, Elasticsearch, MongoDB, etc
- Published papers in ML or a related field
- Presented your work at a reputable scientific or technical conference
