Senior Software Engineer in New York at PurpleLab Inc

The Senior Software Engineer is responsible for leading the design and construction of high-performance data services within the product development team. This role requires the application of expertise in Python, Natural Language Processing (NLP), and large-scale data engineering principles to support critical functions, including health data processing, medical code normalization, and the extraction of valuable information from unstructured health data. This position is central to solving complex, real-world problems in the healthcare domain through robust and scalable data solutions.

DUTIES AND RESPONSIBILITIES:

• Develop scalable Python services to process large healthcare datasets (claims, providers, patients).
• Implement NLP techniques for medical text classification, entity extraction, and coding crosswalks (ICD-10 ? CPT ? DRG).
• Contribute to payer and provider mastering pipelines, improving data accuracy and interoperability.
• Collaborate with data scientists and clinicians to build features in PurpleLab platforms.
• Ensure solutions are compliant with healthcare data privacy/security requirements (HIPAA, HITRUST).
• Optimize system performance and reliability for cloud deployment (AWS).
• Perform other duties as assigned to support business needs and company objectives.

• 5+ years of professional Python development experience.
• Hands-on experience with NLP libraries (spaCy, Hugging Face Transformers, NLTK, scikit-learn).
• Familiarity with healthcare vocabularies (ICD-10, CPT, HCPCS, DRG, SNOMED-CT).
• Strong experience with SQL and data warehouses.
• Proven track record working with high-volume data pipelines.
• Experience with APIs and microservices frameworks (FastAPI, Flask, Django).
• Proficiency in Git, CI/CD, and containerization (Docker).

*Please do not contact human resources, hiring managers or employees directly regarding this position. All communication should go through application portal. Applicants who reach out to individuals outside the designated contact will not receive a response.