Intermediate Data Scientist - Healthcare AI & Data Harmonization - Remote

Company: NTT DATA Services

Location: Philadelphia, Pennsylvania, United States

Salary: $104.2K – $142.5K a year

Work arrangement: Remote possible

Employment type: Full-time

Experience: 2-5 years

Education: bachelor degree, postgraduate degree

Posted: 2026-11-17

Responsibilities

The role involves designing and implementing enterprise-scale data harmonization and automation solutions for healthcare and life sciences datasets. The candidate will develop AI/ML models and data pipelines to normalize, map, and extract insights from structured and unstructured medical information.

Requirements

Candidates must have 3–5 years of professional experience in data science or engineering, with at least 1–2 years in healthcare or life sciences. Proficiency in Python, machine learning frameworks, and knowledge of healthcare data standards like HL7 FHIR or SNOMED CT are required.

Skills

  • Python
  • Machine learning
  • Data harmonization
  • NLP
  • Large language models
  • PySpark
  • SQL
  • Data engineering
  • Healthcare data standards
  • Semantic mapping
  • Deep learning
  • Transformer architectures
  • Data quality
  • Cloud computing
  • MLOps
  • Automation

Benefits

  • Medical insurance
  • Dental insurance
  • Vision insurance
  • Flexible spending account
  • Health savings account
  • Life insurance
  • AD&D insurance
  • Short-term disability coverage
  • Long-term disability coverage
  • Paid time off
  • Employee assistance program
  • 401k program with company match

About this role

Req ID: 398008 
NTT DATA strives to hire exceptional, innovative and passionate individuals who want to grow with us. If you want to be part of an inclusive, adaptable, and forward-thinking organization, apply now.
We are currently seeking a Intermediate Data Scientist - Healthcare AI & Data Harmonization - Remote to join our team in Philadelphia, Pennsylvania (US-PA), United States (US). 
Intermediate Data Scientist – Healthcare AI & Data Harmonization
 
Position Overview
We are seeking an experienced Intermediate Data Scientist to support the development and implementation of enterprise-scale data harmonization and automation solutions within the Healthcare and Life Sciences domain.
This individual will design, develop, and optimize intelligent data processing pipelines that ingest, transform, normalize, and map large volumes of heterogeneous medical data, including structured clinical, genomic, and operational datasets, as well as unstructured information such as clinical notes and pathology reports.
The role will leverage advanced Artificial Intelligence and Machine Learning technologies, including Large Language Models (LLMs), Natural Language Processing (NLP), semantic search, and automated data mapping techniques to improve the accuracy, efficiency, and scalability of medical data harmonization.
The successful candidate will have hands-on experience with Python, machine learning frameworks, big data processing technologies, and healthcare data standards. Exposure to specialized AI computing infrastructure, including NVIDIA GPUs and Google TPUs, will be particularly valuable.
 
Key Responsibilities
Data Mapping & Harmonization

Design and implement automated data mapping pipelines to ingest, normalize, and transform diverse healthcare and life sciences datasets.
Develop solutions to map structured clinical data, including CDISC, EHR, and SDTM datasets, as well as unstructured medical information such as clinical notes and pathology reports.
Implement automated semantic mapping techniques to align source data with established medical terminologies and standardized vocabularies, including SNOMED CT, RxNorm, LOINC, and ICD-10.
Develop reusable mapping frameworks to support data standardization, interoperability, and integration across multiple data repositories.
Identify opportunities to improve mapping accuracy, reduce manual intervention, and increase processing efficiency through AI-driven automation.

AI, Machine Learning & Accelerator Optimization

Develop, fine-tune, and deploy machine learning and deep learning models to support automated data mapping, semantic alignment, and information extraction.
Leverage LLMs, transformer architectures, embedding models, and semantic search techniques to improve contextual understanding of complex medical data.
Optimize AI/ML workloads using specialized hardware accelerators, including NVIDIA GPUs, AMD Instinct, and Google TPUs.
Improve the performance of embedding generation, tokenization, model inference, and semantic matching processes.
Evaluate model accuracy, processing performance, and computational efficiency across different datasets and use cases.

Data Engineering & Pipeline Development

Build and maintain scalable data ingestion, transformation, and processing pipelines capable of handling large, potentially terabyte-scale healthcare datasets.
Develop distributed data processing workflows using PySpark and other big data technologies.
Integrate structured and unstructured data sources into standardized data processing environments.
Implement efficient data transformation, validation, and orchestration processes.
Collaborate with Data Engineers and Architects to ensure pipelines are reliable, scalable, and production-ready.

NLP & Unstructured Medical Data Extraction

Develop and implement NLP and Named Entity Recognition (NER) models to extract relevant clinical information from unstructured medical documents.
Identify and extract medical entities, terminology, relationships, and contextual information from clinical notes, pathology reports, and other healthcare documentation.
Apply entity recognition, classification, normalization, and semantic matching techniques to convert unstructured information into structured datasets.
Evaluate and improve extraction accuracy through model testing, validation, and iterative refinement.

Data Quality, Governance & Compliance

Develop automated data quality and validation frameworks to ensure the accuracy, completeness, consistency, and reliability of harmonized datasets.
Establish validation processes for AI-generated mapping outputs and standardized medical terminology.
Support data lineage, reproducibility, traceability, and documentation across data processing workflows.
Ensure solutions align with applicable healthcare data privacy and regulatory requirements, including HIPAA and GDPR.
Collaborate with Data Governance and Compliance teams to support secure and responsible handling of sensitive healthcare information.

 
Required Qualifications

3–5 years of professional experience in Data Science, Machine Learning Engineering, Data Engineering, or Applied AI.
1–2+ years of experience working within Healthcare, Life Sciences, Biotechnology, or Pharmaceutical environments.
Practical experience developing and deploying machine learning models, AI-driven data processing solutions, or automated data transformation pipelines.
Strong Python programming skills and experience working 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 requirements in regulated or privacy-sensitive environments.

 
Technical Skills & Qualifications
AI, Machine Learning & Hardware Acceleration
...

About NTT DATA Services

IT Services and IT Consulting · 10,001+ employees · headquartered in Plano, Texas

See all my matches — 2 min, free

More Data Scientist Jobs

87 new Data Scientist jobs were posted this week.

All Remote Data Scientist Jobs →

Get new Data Scientist jobs by email — start free

Other Jobs in Philadelphia

Before you apply, check your resume against ATS filters for free.