Senior Data Engineer

Role Description

As a Senior Data & Software Engineer focused on agentic AI, you will help design, build, and maintain the intelligent data pipelines and automation systems that enable Vytalize Health to scale its data source coverage without linearly scaling the team. Working cross-functionally, your solutions will drive better patient outcomes by accelerating the normalization and governance of clinical and claims data. You will be part of a small, high-performing healthcare data engineering team where engineers support each other's growth through mentorship and tight collaboration.

• Lead development of the agentic connector pipeline — automating source profiling, field mapping, dbt model generation, and validation
• Design and build AI-assisted data ingestion workflows using LLM APIs and agentic orchestration frameworks
• Own the first 2–3 end-to-end agent-built connectors as proof of concept for the broader team
• Establish internal AI tooling standards and patterns; mentor team on agentic development practices
• Design, build, and maintain data pipelines and systems to meet business needs
• Implement data quality control processes and contribute to observability frameworks
• Document new and existing systems, designs, processes, and procedures
• Work on-call 3–9% of the year, one week at a time, to support production failures and emergent business needs
• Mentor and learn from colleagues through pair/mob programming, design reviews, and Lunch & Learns

Qualifications

• 5+ years of experience in data engineering or a related field
• 1–2+ years of hands-on experience building with LLM APIs and agentic frameworks
• Strong Python and SQL proficiency
• Experience with Databricks and AWS
• Strong understanding of data lake architecture, data modeling, and medallion patterns (Bronze/Silver/Gold)
• Experience building and consuming APIs
• Experience with data quality control and pipeline observability
• Strong debugging, problem-solving, and analytical skills
• Excellent written and verbal communication skills
• Comfortable working in a fast-moving, ambiguous environment

Requirements

• Strong Pluses
• Experience with dbt and modern data transformation patterns
• Familiarity with healthcare data formats: CCDAs, 837s, FHIR APIs, CDS Hooks, HL7
• Experience with Tuva or similar clinical data normalization frameworks
• Knowledge of Value-Based Care and Accountable Care Organizations
• Experience with EHR integrations (Epic, NextGen, Athena, ECW)
• Familiarity with orchestration tools (Databricks Workflows, Airflow, or equivalent)
• Experience in a startup or high-growth environment