Machine Learning/Data Engineer

About Carda 

Rehab is a pain. So much so that only 10% of qualifying Cardiac and Pulmonary patients attend. At Carda Health, we’ve reimagined rehab. Our program allows patients to complete inspiring, convenient, life-saving therapy remotely.

Who are we?

We are a team of clinicians, data scientists, mathematicians and repeat entrepreneurs. And a few recovering financiers. Our belief is that technology and data, when applied to the right problem, transforms people’s lives and changes even the most entrenched industries.

Carda was founded by Harry and Andrew, two friends from Wharton who share a family history of heart disease and experience with poor access to care. We now work with some of America’s largest and top-ranked hospitals and most innovative insurers. We are fortunate to be backed by some of the best investors in the business who have also backed the likes of Livongo, Hinge, Calm, MDLive, and others.

What we're looking for

We’re looking for a Machine Learning/Data Engineer to lead the development of ML applications and data infrastructure that will accelerate our ability to gather actionable, high-impact insights from complex healthcare data. We’re looking for someone who is effective at all levels of the machine learning and data stack, with a track record of delivering applications from the ground up.

You’ll lead research, prototyping, and deployment of models that risk stratify patients, predict readmissions, surface timely interventions for our clinicians, and more. As one of our early data hires, you’ll have significant ownership over architecture and technology decisions and your work will help set the long-term technical vision for all our future data initiatives.

In this role, you'll:

• Build and own our data infrastructure to ingest, store, and process large volumes of healthcare data
• Build and deploy robust ML pipelines, including data extraction, feature development, model training, testing, and deployment
• Collaborate with the rest of the engineering team to integrate ML and AI applications into user-facing production systems
• Continuously monitor, evaluate, and optimize the performance of deployed models to ensure they meet business goals and provide high-quality user experiences
• Collaborate with product, engineering, clinical, and operations teams to translate business needs into data and ML solutions
• Implement engineering best practices for CI/CD, automated testing, and model versioning

What you bring to the team:

• 4+ years of ML engineering experience in a professional setting with a proven track record of owning the end-to-end machine learning lifecycle, including data ingestion, preprocessing, model training, deployment, and production monitoring
• 2+ years of experience with modern machine learning tools and libraries (scikit-learn, PyTorch, TensorFlow, spaCy, etc) with strong proficiency in Python
• 2+ years of experience with any of the following fundamental AI technologies: vector search, embedding models, recommender systems, supervised, unsupervised machine learning, deep learning, LLM orchestration, RAG systems, etc
• Familiarity with cloud services and MLOps tooling to deploy and scale data and ML workloads cost-effectively
• Familiarity with data warehouses (Redshift, BigQuery, Snowflake, etc) and best practices around data pipeline tools
• Strong proficiency in SQL
• Comfort with ambiguity and short feedback loops
• A passion for building products that make a real-world impact

Bonus if you have:

• Professional experience with healthcare applications of machine learning, AI, and data engineering
• Experience working with HIPAA compliant applications and healthcare data (FHIR, HL7, clinical notes, etc.)
• Previous experience at an early-stage startup