Senior AI Engineer

About Lantern Lantern is the specialty care platform connecting people with the best care when they need it most. By curating a Network of Excellence comprised of the nation's top specialists for surgery, cancer care, infusions and more, Lantern delivers excellent care with significant cost savings to employers and their workforces. Lantern also pairs members with a dedicated care team, including Care Advocates and nurses, for the entirety of their care journey, helping them get back to good health, back to their families and back to work. With convenient access to specialists nationwide, Lantern means quality care is within driving distance for most. Lantern is trusted by the nation's largest employers to deliver care to more than 6 million members across the country. Learn more about us at lanterncare.com. Lantern is seeking a Senior AI Engineer to drive the design, development, and scaling of our Generative AI and agentic systems. In this role, you will take technical ownership of complex LLM-powered applications and multi-agent workflows, set the engineering standard for AI development practices, and partner closely with engineering leadership, product, clinical operations, and data teams to translate strategic priorities into production-grade AI solutions. You are a seasoned AI practitioner who has shipped production LLM and agentic systems, can reason through architectural trade-offs, and brings both depth (GenAI, RAG, agents, LLMOps) and breadth (software engineering, data infrastructure, cloud platforms). Beyond building, you will lead design and code reviews, mentor engineers, and actively shape how Lantern builds and operates AI at scale in a regulated healthcare environment. Locations : We prefer Hybrid - at least 3 days/wk in either our Dallas, TX or New York, NY offices Responsibilities: Generative AI & LLM Architecture Architect and deliver production LLM-powered capabilities including advanced RAG pipelines, structured extraction, multi-document reasoning, dialogue systems, and domain-specific language models. Own prompt engineering strategy: design versioned, testable prompt pipelines; establish team standards for prompt management, evaluation, and continuous improvement. Lead the selection and integration of embedding models, vector databases (e.g., Azure AI Search, Pinecone, Weaviate), and hybrid retrieval architectures; drive systematic retrieval quality improvement. Define and implement LLM evaluation frameworks and automated quality benchmarks; establish guardrails, grounding strategies, and hallucination mitigation controls meeting healthcare compliance standards. Evaluate frontier and open-source models (GPT-4.5, GPT-5.x, Claude, Gemini, Llama, Mistral, etc.); lead model selection decisions and maintain awareness of the evolving AI landscape to inform roadmap choices. Agentic Systems Design & Leadership Lead the architecture and implementation of production agentic systems — including multi-agent orchestration, planning, tool-use, memory, and state persistence — using frameworks such as LangGraph, AutoGen, CrewAI, or custom layers. Design robust human-in-the-loop mechanisms, approval workflows, fallback strategies, and audit trails to ensure agentic systems meet safety, compliance, and clinical trust requirements. Establish patterns for tool-use and function-calling that allow agents to interact reliably with external APIs, clinical systems, and internal data services. Define standards for agent observability: trace logging, step-level monitoring, behavioral drift detection, and structured evaluation of multi-step agent runs. Engineering Leadership & MLOps Write production-quality, modular, and well-tested code; set the technical bar through rigorous design and code reviews across the AI engineering team. Architect and maintain LLM inference services, API integrations, and supporting data pipelines on Azure; drive performance, reliability, and cost optimization. Define and champion LLMOps practices: pro…