JobID: 394355
Category: Software Engineering
JobSchedule: Full time
Posted Date: 2026-10-23T22:04:47+00:00
JobShift:
Hours / Pay Period: 80
This is a hybrid position and must be located within 100 miles of a Mayo Clinic campus for occasional on-site expectations based on business needs.
As a Senior Software Engineer for AI Platform Engineering, you will bridge the gap between high-scale systems architecture and frontier AI. You will be one of architects and builders of our Model & Agent Runtimes-the specialized engines that govern how models and autonomous agents execute across our hybrid-cloud footprint.
This isn't just about deployment; it's about a platform-first mindset. You will ensure that AI capabilities are scalable, secure, and governed through world-class AgentOps, LLMOps, and MLOps practices.
What You'll Do
- Architect the Future of Runtimes: Design and implement high-performance hosting environments for both specialized models and autonomous agents.
- Scale Hybrid-Cloud Infrastructure: Build multi-tenant platform capabilities that support seamless agent and model execution across diverse cloud and on-prem environments.
- Drive Operational Excellence: Implement robust solutions for real-time monitoring, distributed tracing, and automated evaluation of agents & models in production.
- Operational Stewardship: Act as a member of our rotational platform operational team, ensuring the reliability and uptime of critical AI services.
- Collaborate & Advocate: Partner with cross-functional AI teams to identify system friction, streamlining their workflows and accelerating the delivery of AI-driven value.
What You'll Bring
- Deep Systems Expertise: Proven experience building scalable back-end systems, ideally with a focus on containerization and orchestration (Kubernetes).
- AI/ML Fluency: Strong understanding of the lifecycle of LLMs and autonomous agents, including inference optimization and RAG architectures.
- Operational Rigor: A track record of implementing observability (logging, metrics, tracing) in complex, distributed environments.
- Problem-Solving Mindset: The ability to turn abstract AI research into production-grade, hardened platform features.
Why this team? We are moving beyond simple model serving. We are building the foundational "nervous system" for autonomous agents in a high-stakes environment where performance and governance are non-negotiable.