Our unique, rapidly growing data streams are enabling novel opportunities to manage clinical trials more efficiently and predictably. The Data Products division is looking for talented Senior Machine Learning Engineers to enrich our solutions offerings with enhanced intelligence both from internal tactical R&D and through productization of data science efforts. If you are empathetic, business-driven, and want to use your machine learning skills to make a tangible impact in the clinical research community then this may be the role for you.

As a fast-growing company, we're looking for people who can effectively balance rapid execution and delivery with sustainable and scalable ML initiatives to serve the business most effectively. You have strong opinions, weakly held, and while well-versed technically know when to choose the right tool, for the right job, at the right level of complexity. You will work closely with our Data Engineering and Data Science & Analytics divisions, and the Product and Product Engineering departments to deliver enterprise-ready intelligence solutions to internal and external stakeholders.

What You'll Be Working On

• Expanding our information extraction and structured knowledge annotation and classification systems to support explainable recommendations for enhancing trial enrollment to research sites and sponsors
• Modularizing and converting data science models into well-supported, enterprise-ready deliverables through a scalable ModelOps/MLOps pipeline
• Developing machine learning solutions to help optimize and scale logistics around trial management and orchestration
• Becoming intimately familiar with HIPAA, GDPR, and other applicable regulatory frameworks and how they influence our architecture and development decisions, especially for historically underrepresented or underserved populations
• Frequently communicating your efforts to the Data Products Lead and other technical/non-technical stakeholders in clear written, verbal, or presentation form
• Living our data philosophy, which focuses on ethical decision making, being aware of how biased data (and assumptions) can affect results (and people), and being laser-focused on business needs

What You Bring To Reify Health

• At least 4 years of professional work experience in an enterprise role developing data products using regulated data, ideally in the health or clinical domains
• Experience with practical application of Information Extraction techniques, NLP, search optimization, EDA techniques, logical/probabilistic inference, neural networks, supervised/unsupervised learning, and integration of domain-specific taxonomies and ontologies (e.g. UMLS, SNOMED, LOINC)
• Deeply understand not only how to use a technique but why it is or is not appropriate in a given situation, with available data, and for specific business needs
• Expertise in Python (or Clojure!), advanced SQL, and the ability to work with (or ramp up to support) data science work developed in R
• Comfort with working with data from varied structured relational/non-relational and unstructured sources
• Ideally some familiarity with our stack, including: AWS (Redshift, S3, MSK, Lambda), dbt, Postgres, Prefect, Terraform, Kafka, Docker
• Understanding of the nuances of testing and addressing scalability/accuracy of machine learning applications at enterprise scale and the management of such applications through ModelOps/MLOps systems
• Advanced degree in computer science, applied mathematics, or other related field
• Relevant published or publicized professional or academic work such as open-source contributions, blog posts, or publications