Staff Software Engineer, Data Extraction

Pivotal Health•,

13d•$210,000 - $240,000

About The Position

Pivotal Health is expanding its investment in clinical data infrastructure as a core strategic initiative. We are building a state-of-the-art clinical data platform that collects, processes, and transforms complex healthcare information from a variety of sources and formats into structured, high-quality data assets. This platform serves as the foundation for a growing set of products, analytics capabilities, and operational workflows across the organization. As healthcare data continues to grow in volume and complexity, building systems that securely process, govern, and deliver high-quality clinical data has become a critical capability. This engineer will own key systems within that platform, helping define how clinical data is ingested, processed, normalized, and delivered at scale. As a Staff Software Engineer focused on Data Extraction, you will design and build the ingestion, parsing, normalization, and enrichment pipelines that turn messy healthcare data into structured assets. You'll work across OCR technologies, document processing frameworks, healthcare interoperability standards, and large-scale data extraction and processing systems. Your work will directly power claims evidence generation, provider advocacy initiatives, and efforts to improve Independent Dispute Resolution (IDR) outcomes and win rates. This role is ideal for someone who enjoys solving difficult data problems where there is no clean source of truth. You'll thrive here if you're excited by large-scale healthcare datasets, ambiguous technical challenges, and the opportunity to define foundational systems that will influence product strategy for years to come.

Requirements

8+ years building backend software systems in production environments.
Experience with healthcare data standards such as HL7, FHIR, CDA, or EHR integrations.
Familiarity with medical records, claims, or healthcare operations.
Experience designing large-scale data processing or document processing platforms, specifically working with clinical data - familiarity with medical terminology/coding practices.
Strong proficiency in Python and SQL, or similar backend languages.
Experience working with unstructured data and NLP systems.
Proven ability to design systems that operate reliably across imperfect or incomplete datasets.
Experience making architectural decisions that influence multiple teams or business functions.
Comfortable operating in ambiguous environments where requirements evolve as the business learns.
Demonstrated bias toward ownership and delivering outcomes rather than simply completing tickets.

Nice To Haves

Experience with healthcare data standards such as HL7, FHIR, CDA, or EHR integrations.
Experience building LLM-powered extraction or document understanding systems.
Experience with machine learning workflows.

Responsibilities

Own clinical data extraction architecture. Design and evolve the systems that ingest, process, and normalize structured and unstructured clinical data from multiple healthcare sources.
Build document intelligence pipelines. Develop services that extract meaningful information from PDFs, scanned records, images, and clinical documentation.
Lead healthcare data modeling efforts. Create approaches for transforming raw clinical artifacts into structured, queryable datasets.
Develop scalable ingestion services. Design resilient systems capable of processing large volumes of healthcare records with high reliability and accuracy.
Build scalable data extraction systems. Leverage the best available technologies and architectural approaches to improve information extraction, classification, and normalization across diverse healthcare data sources.
Establish data quality standards. Create validation frameworks, monitoring systems, and feedback loops that improve extraction accuracy over time.
Influence and collaborate across clinical, product, engineering, data, and operational domains: Driving alignment on business objectives and translating them into technical systems that support provider evidence generation.
Drive technical strategy for unstructured healthcare data. Evaluate technologies, standards, and architectural approaches that accelerate clinical data adoption.
Mentor engineers across the organization. Raise engineering standards through design reviews, technical leadership, and hands-on collaboration.