Jobs → Engineering → Senior AI/ML Engineer

About the Role We are seeking an experienced Senior AI/ML Engineer to join a dynamic engineering team responsible for developing and scaling a production-grade healthcare conversational AI platform. This role will focus on backend service development, AI agent workflows, and system integrations that support patient-facing conversational experiences. Key Responsibilities • Design, develop, and maintain backend APIs and services using Python 3.12+ and FastAPI • Develop and enhance multi-agent AI orchestration workflows using LangGraph, LangChain, or PydanticAI • Integrate and optimize large language model providers, including OpenAI, Anthropic, and Google GenAI • Work with Azure services such as Cosmos DB, App Configuration, Key Vault, Event Hubs, and Application Insights • Develop and maintain task handlers for domain-specific workflows (e.g., care tasks, medications, scheduling) • Implement input and output guardrails, prompt engineering techniques, and AI safety patterns • Collaborate on architectural decisions, code reviews, and production support activities • Develop and maintain automated test suites using pytest Requirements • A minimum of five years of professional software development experience • Strong proficiency in Python, with demonstrated production experience using FastAPI or comparable asynchronous frameworks • Hands-on experience with LLM orchestration frameworks such as LangGraph, PydanticAI, or equivalent systems • Solid understanding of prompt engineering, retrieval augmented generation (RAG) patterns, and AI guardrails • Experience with Azure cloud services, including Cosmos DB, Azure Key Vault, and App Configuration • Familiarity with Docker, CI/CD Pipeline (e.g., GitHub Actions), and containerized deployments • Strong knowledge of JWT/OAuth authentication mechanisms and Securing Apigee APIs best practices • Ability to operate effectively within a small, fast-paced team environment with a high degree of ownership