GenAI Data Scientist – Medical Imaging, RIS & Healthcare Services
Role Overview
We are seeking a GenAI Data Scientist with strong expertise in medical imaging, radiology workflows (RIS/PACS/VNA), and service-oriented healthcare platforms. This role will focus on designing, training, and deploying Generative AI and Agentic AI solutions that improve clinical efficiency, operational intelligence, reporting automation, and service optimization across healthcare systems.
You will work closely with product managers, clinical SMEs, engineering teams, and cloud architects to translate healthcare problems into scalable AI-driven solutions.
Key Responsibilities
Generative AI & ML Development
Design and develop LLM-powered and multimodal AI solutions for:
Radiology reporting automation
Imaging analytics and insights
Clinical decision support
Operational and service intelligence
Build agentic AI workflows for tasks such as:
Study triage and prioritization
Report quality checks
Workflow optimization across RIS/PACS/VNA
Fine-tune and evaluate LLMs and vision-language models using domain-specific medical datasets.
2. Medical Imaging & Radiology Domain Applications
Work with DICOM, non-DICOM, and multimodal data (images, text, metadata, audio/video).
Develop AI models for:
Image understanding and feature extraction
Metadata enrichment and study classification
Automated measurements and annotations
Collaborate with clinical experts to ensure clinical relevance, safety, and interpretability of AI outputs.
3. Data Engineering & Model Lifecycle
Build robust data pipelines for ingesting data from RIS, PACS, VNA, and service platforms.
Perform data curation, labeling strategies, feature engineering, and dataset versioning.
Implement model evaluation, monitoring, drift detection, and continuous learning pipelines.
4. Healthcare Services & Operations Intelligence
Apply AI to non-clinical service use cases, including:
Turnaround time (TAT) optimization
Resource utilization and scheduling
SLA adherence and predictive alerts
Revenue leakage and operational bottlenecks
Build AI-driven dashboards, summaries, and conversational analytics for executives and operations teams.
5. Deployment, MLOps & Cloud
Package and deploy AI models as APIs and microservices.
Implement MLOps best practices:
CI/CD for models
Model registry and versioning
Observability and performance tracking
Work on cloud-native deployments (AWS / GCP / Azure), ensuring scalability, security, and compliance.
6. Compliance, Ethics & AI Safety
Ensure solutions comply with HIPAA, GDPR, and healthcare data privacy standards.
Implement explainability, auditability, and bias mitigation in AI models.
Participate in AI governance and responsible AI initiatives.
