Note: The job is a remote job and is open to candidates in USA. Banyan Software is dedicated to acquiring and growing software businesses, focusing on modernizing through AI expertise. They are seeking an experienced AI Engineer to design and implement AI-native capabilities within their healthcare SaaS platform, MedicatOne, enhancing how healthcare organizations interact with their data and workflows.

Responsibilities

• Design and implement AI-powered capabilities within the MedicatOne platform
• Integrate modern AI models and services into production workflows
• Develop systems that interact with structured application data and APIs
• Ensure AI features are reliable, performant, and secure
• Work with large datasets related to healthcare operations
• Design systems that leverage structured data effectively
• Build logic that enables intelligent interpretation of operational data
• Collaborate with engineering on data pipelines, schemas, and analytics frameworks
• Integrate AI capabilities into existing SaaS architecture
• Work with backend engineers to ensure scalable system design
• Optimize performance of data-intensive AI workflows
• Contribute to platform-level architecture decisions
• Ship production-ready AI features quickly and iteratively
• Collaborate closely with leadership on prioritization and implementation
• Help establish best practices for AI development within the organization

Skills

• 5+ years building production SaaS systems
• Direct experience building and implementing AI/ML or LLM-based features
• Strong experience working with structured data and analytics systems
• Experience working with healthcare data or healthcare SaaS environments, including familiarity with the regulatory, privacy, and compliance considerations that shape technical decisions (HIPAA, PHI handling, de-identification)
• Demonstrated ability to build and deploy systems end-to-end
• Working knowledge of modern AI infrastructure and patterns, including LLM API integration (OpenAI, Anthropic, or similar) in production environments
• Retrieval-Augmented Generation (RAG): designing retrieval pipelines, chunking strategies, and grounding LLM responses in real data
• Vector databases: embedding, indexing, and querying unstructured or semi-structured data
• Data modeling and SQL
• Data pipelines and analytics workflows and working with large structured datasets
• API design and backend services
• Working with large, structured datasets

Company Overview