AI Engineer (LLMs for Healthcare)

Keebler Health is building the operating system for value-based care, aiming to help healthcare organizations thrive by unlocking the full power of their data. They are seeking a talented AI Engineer with expertise in developing large language models and healthcare workflows to drive innovation in Value-Based Care solutions.

Responsibilities:

• Fine-tune and optimize large language models (LLMs) to address specific healthcare applications
• Develop and apply advanced prompt engineering techniques to enhance model outputs for clinical scenarios
• Implement Retrieval-Augmented Generation (RAG) systems to improve knowledge retrieval from large datasets
• Work with knowledge graphs to organize and integrate healthcare-specific data for enhanced decision-making
• Evaluate black-box models using precision, recall, and other performance metrics, ensuring robustness and reliability
• Collaborate with healthcare professionals to understand workflows and identify opportunities for AI-driven enhancements
• Design and build AI models that align with healthcare standards and regulations (e.g., HIPAA compliance)
• Integrate domain-specific knowledge of healthcare data, including FHIR and interoperability standards, into AI solutions
• Develop and maintain scalable, production-ready AI pipelines using MLOps tools
• Deploy and monitor AI models in production environments to ensure performance and compliance
• Optimize infrastructure for efficient training, testing, and deployment of models
• Stay at the forefront of advancements in AI, especially in healthcare applications
• Identify and resolve performance bottlenecks in AI workflows
• Explore emerging trends and technologies in LLMs and healthcare to continually improve solutions
• Partner with cross-functional teams, including data engineers and clinicians, to ensure seamless integration of AI into healthcare workflows
• Communicate technical results and insights effectively to non-technical stakeholders

Requirements:

• Proven experience in LLM fine-tuning and advanced prompt engineering
• Strong background in Python and modern ML frameworks (e.g., Huggingface, pyTorch)
• Familiarity with healthcare workflows and regulatory requirements (e.g., HIPAA, FHIR standards)
• Hands-on experience with retrieval-augmented generation (RAG) techniques
• Expertise in evaluating AI models using performance metrics like precision, and recall
• Experience with MLOps frameworks such as MLflow, Langfuse, or similar tools
• Understanding of healthcare data standards, including HL7 and HEDIS metrics
• Strong problem-solving skills in integrating AI with complex healthcare datasets
• Familiarity with cloud platforms (e.g., AWS, GCP, or Azure) and containerization (Docker, Kubernetes)