Clinical Science Informaticist

Oracle Oracle · Enterprise · United States

This role focuses on leveraging clinical data, machine learning (ML), and AI technologies to drive healthcare innovation. The individual will apply informatics techniques, statistical modeling, and annotation guidelines to improve healthcare delivery and patient outcomes. Key responsibilities include supporting data annotation, creating annotation guidelines, developing evaluation frameworks for AI models, and defining AI red teaming and guardrails. The role also involves understanding the AI model life cycle, data preprocessing, feature engineering, and model development for AI/ML applications within the healthcare domain.

What you'd actually do

  1. Creation of evaluation frameworks for the performance AI models.
  2. Defining AI red teaming and guardrails in collaboration with applied scientists.
  3. Conduct error analysis of AI model outputs.
  4. Oversee the collection, cleaning, and pre-processing of data, ensuring datasets are ready for analysis and model training.
  5. Define requirements for establishing the effectiveness of AI/ML models by designing ground truth algorithms and performance metrics for outcome validation.

Skills

Required

  • Clinical experience in roles such as a registered nurse, pharmacist, clinical laboratory technician, respiratory therapist, or other clinical roles.
  • Proven experience in clinical informatics, including familiarity with clinical EHR systems and data, as well as collaboration with healthcare professionals, IT specialists, and business users to analyze workflows and identify opportunities for improvement.
  • Strong background in working with clinical data to support evidence-based decision making, quality measurement, care coordination, and outcomes-based improvement programs.
  • Hands-on experience in supporting data annotation, creating and maintaining annotation guidelines, machine learning (ML), natural language processing (NLP), and AI-driven projects within the healthcare domain.
  • Creation of evaluation frameworks for the performance AI models.
  • Understanding of the AI model life cycle
  • Experience at the intersection of statistical methods, machine learning techniques, and generative AI and medical standards and ontologies.
  • Expertise in data preprocessing, feature engineering, and model development for AI/ML applications, with a focus on clinical data integration.
  • Experience in defining data requirements, ensuring data readiness, and validating annotated data for AI/ML solutions.
  • Proficient in working with clinical terminologies such as SNOMED CT, ICD, LOINC, and CPT, and utilizing them in data science models and algorithms.
  • Familiarity with healthcare data standards such as FHIR Resources, QDM Categories, and experience modeling clinical and administrative healthcare data for AI-driven solutions.
  • Proven ability to implement quality control processes for ensuring the integrity, reliability, and clinical relevance of data used in AI/ML applications.
  • Experience in working with disparate healthcare data types, including EHR, billing, lab, eligibility, and claims data, to drive insights and improve healthcare outcomes.
  • Create and curate clinical value sets composed of industry-standard terminologies such as SNOMED CT, ICD, and CPT, ensuring alignment with data science models, organizational data models, and algorithms.
  • Develop and document clear annotation guidelines to ensure they are understood by annotation teams and data scientists.
  • Define data requirements and ensure integration within AI/ML-driven applications, with a focus on data quality and model readiness.
  • Implement quality control processes to validate the integrity and reliability of annotated data, ensuring suitability for AI/ML solutions.
  • Lead annotation review cycles and provide feedback to ensure labeling quality, while performing regular evaluations of model predictions to identify edge cases and improve performance.
  • Defining AI red teaming and guardrails in collaboration with applied scientists.
  • Conduct error analysis of AI model outputs.
  • Recognized as a subject matter expert within the team and provide mentorship to less experienced team members.
  • Drive internal platform changes including data models, terminology ontologies, and the platform rules engine to ensure data compatibility with AI/ML models.
  • Oversee the collection, cleaning, and pre-processing of data, ensuring datasets are ready for analysis and model training.
  • Define requirements for establishing the effectiveness of AI/ML models by designing ground truth algorithms and performance metrics for outcome validation.
  • Collaborate with cross-functional teams, including data scientists, annotators, engineers, and project managers, to enhance data quality and success across AI-driven projects.
  • Contribute to model evaluation and performance monitoring, ensuring data-driven insights meet clinical objectives.
  • Continue to drive and implement AI driven automated processes, both within the annotation framework and other job expectations
  • Strong critical thinking and problem-solving skills, particularly for designing algorithms and models that meet clinical and business objectives within real-world healthcare data constraints.
  • Experience working with disparate healthcare data including EHR, billing, lab, eligibility, or claims data.
  • Expertise in clinical and administrative healthcare data modeling using industry standards such as FHIR Resources, QDM Categories, and other healthcare data formats.
  • Advanced knowledge of data science techniques including statistical analysis, machine learning, and natural language processing (NLP).
  • Proficiency in programming languages such as Python, R, or SQL for healthcare data analysis and model development.
  • Experience with AI/ML frameworks such as TensorFlow, PyTorch, or scikit-learn.
  • Familiarity with industry-standard terminologies such as SNOMED CT, ICD, LOINC, and CPT, and their application in data science models.
  • Knowledge of care management best practices and services and their integration with AI/ML models.
  • Strong ability to interpret complex clinical and business requirements, transforming them into actionable data guidelines and annotations.
  • Excellent communication and collaboration skills, working effect

Nice to have

  • Life sciences, clinical trials, and regulatory experience is a plus.

What the JD emphasized

  • Hands-on experience in supporting data annotation, creating and maintaining annotation guidelines, machine learning (ML), natural language processing (NLP), and AI-driven projects within the healthcare domain.
  • Creation of evaluation frameworks for the performance AI models.
  • Defining AI red teaming and guardrails in collaboration with applied scientists.
  • Expertise in data preprocessing, feature engineering, and model development for AI/ML applications, with a focus on clinical data integration.
  • Proven ability to implement quality control processes for ensuring the integrity, reliability, and clinical relevance of data used in AI/ML applications.

Other signals

  • AI-driven projects
  • machine learning (ML)
  • natural language processing (NLP)
  • evaluation frameworks for AI models
  • data annotation
  • AI red teaming
  • guardrails