Intermediate Data Scientist - Healthcare AI Data Harmonization
Artificial Intelligence
Data Analysis
Data Integration
Data Pipeline
Data Processing
Data Science
ETL
Healthcare Ai
Healthcare Data Integration
Healthcare Data Integration Standards
Healthcare Data Interoperability
Healthcare Data Science
Healthcare Nlp
Integration
Large Language Models
Machine Learning
Job Description
Transform healthcare data for AI at scale. NTT DATA offers the chance to work on healthcare AI data harmonization and automation in a role based in Philadelphia, PA (remote). This position blends applied machine learning with healthcare data standards to improve semantic alignment, data quality, and end-to-end pipeline performance. Compensation for this remote role starts at $104,194-$142,500 USD per year (final pay varies by factors such as location and experience).
What you’ll do
- Design and implement automated data mapping pipelines to ingest, normalize, and transform diverse healthcare and life sciences datasets.
- Build solutions that map structured clinical data (including CDISC, EHR, and SDTM) and extract structured information from unstructured medical sources such as clinical notes and pathology reports.
- Apply automated semantic mapping techniques to align source data with standardized medical terminologies, including SNOMED CT, RxNorm, LOINC, and ICD-10.
- Create reusable mapping frameworks to support data standardization, interoperability, and integration across multiple repositories.
- Use AI-driven automation to identify mapping accuracy improvements, reduce manual intervention, and increase processing efficiency.
- Develop, fine-tune, and deploy machine learning and deep learning models for automated mapping, semantic alignment, and information extraction.
- Leverage LLMs, transformer architectures, embedding models, and semantic search to improve contextual understanding of complex medical data.
- Optimize AI/ML workloads using specialized accelerators, including NVIDIA GPUs, AMD Instinct, and Google TPUs, and improve embedding generation, tokenization, inference, and semantic matching performance.
- Evaluate accuracy, processing performance, and computational efficiency across datasets and use cases.
- Build scalable ingestion and transformation pipelines that can handle large, potentially terabyte-scale healthcare datasets.
- Develop distributed processing workflows using PySpark and other big data technologies.
- Integrate structured and unstructured data sources into standardized processing environments and implement transformation, validation, and orchestration workflows.
- Collaborate with Data Engineers and Architects to deliver pipelines that are reliable, scalable, and production-ready.
- Develop NLP and Named Entity Recognition (NER) models to extract clinical information and medical entities, terminology, relationships, and context from healthcare documentation.
- Apply entity recognition, classification, normalization, and semantic matching to convert unstructured information into structured datasets, then validate and refine extraction accuracy.
- Create automated data quality and validation frameworks to ensure accuracy, completeness, consistency, and reliability of harmonized datasets, including validation processes for AI-generated mapping outputs.
- Support data lineage, reproducibility, traceability, and documentation across workflows.
- Ensure alignment with applicable healthcare privacy and regulatory requirements, including HIPAA and GDPR, and collaborate with Data Governance and Compliance teams for secure handling of sensitive information.
What you bring
- 3–5 years of professional experience in Data Science, Machine Learning Engineering, Data Engineering, or Applied AI.
- 1–2+ years of experience in Healthcare, Life Sciences, Biotechnology, or Pharmaceutical environments.
- Practical experience developing and deploying ML models, AI-driven data processing solutions, or automated data transformation pipelines.
- Strong Python skills and experience with structured and unstructured datasets.
- Experience with NLP, semantic search, embeddings, transformer models, or LLM-based applications.
- Understanding of healthcare data structures, medical terminology, and clinical data standards.
- Experience working with large datasets and distributed data processing environments.
- Familiarity with data quality, validation, and governance in regulated or privacy-sensitive settings.
Benefits
- Medical, dental, and vision insurance with an employer contribution
- Flexible spending or health savings account
- Life and ADD insurance
- Short- and long-term disability coverage
- Paid time off
- Employee assistance
- Participation in a 401k program with company match
- Additional voluntary or legally-required benefits
Tech stack you may work with
- Python, PyTorch, TensorFlow, Hugging Face Transformers, Pandas, NumPy
- Large Language Models (LLMs), transformer architectures, embedding models, semantic search, NLP, NER, LLM-based applications
- Distributed and orchestration tools: PySpark, Apache Airflow, Prefect, CI/CD practices
- Cloud and data platforms: Databricks, AWS EMR, Google Cloud Dataproc
- Hardware acceleration and deployment: CUDA, TensorRT, Triton Inference Server, NVIDIA GPUs, AMD Instinct, Google TPUs
- Healthcare standards and vocabularies: CDISC, EHR, SDTM, SNOMED CT, RxNorm, LOINC, ICD-10, OMOP Common Data Model, HL7 FHIR, HL7, UMLS
- Privacy and compliance: HIPAA, GDPR
- Development tooling: Git, Docker
Pay transparency
- Where required by law, NTT DATA provides a reasonable range of compensation for specific roles.
- The starting pay range for this remote role is $104,194-$142,500 USD.
- Actual compensation depends on factors including candidate work location, relevant experience, technical skills, and other qualifications.