Description

You will architect and implement generative AI systems tailored for biomedical data, ensuring HIPAA compliance and seamless integration with existing EHR infrastructure.

Responsibilities

• Architect and optimize transformer-based generative models, including GANs, VAEs, and Diffusion Models, for synthetic medical image generation and patient record synthesis.
• Fine-tune pre-trained LLMs for drug discovery, clinical trial summarization, and medical literature analysis while implementing strategies to mitigate hallucinations in clinical decision support.
• Design scalable GenAI platforms that integrate with EHR systems via APIs, ensuring real-time inference and secure data exchange in multi-cloud environments.
• Establish MLOps workflows, including CI/CD pipelines, model versioning, and traceability, using tools like MLflow and Kubeflow to ensure reproducibility and regulatory compliance.
• Lead the development of cloud-native microservices using Python and FastAPI, managing container orchestration with Kubernetes to support scalable model deployment.

Required Skills

• 7+ years of experience in AI/ML, deep learning, and GenAI architectures.
• Hands-on expertise with LLMs, RAG systems, LangChain, LangGraph, and vector databases.
• Proficiency in Python, FastAPI, and cloud platforms (AWS, Azure, GCP).
• Experience with MLOps tools and practices, including MLflow, Kubeflow, and CI/CD.
• Deep understanding of healthcare data standards (FHIR, HL7) and compliance frameworks (HIPAA, GDPR).
• Strong foundation in optimizing training pipelines for domain-specific nuances in biomedical data.
• Ability to design APIs optimized for multi-cloud and hybrid environments.

Preferred Skills

• Experience with TensorFlow and PyTorch for model training and evaluation.
• Background in implementing data anonymization techniques for synthetic data generation.

Key Skills

Education

Any Graduate