Staff AI Engineer

Staff AI Engineer at Micron (Boise, ID, onsite) to build modern AI-first full stack applications and production systems, with a focus on custom AI agents, MCP, and operationalizing AI for manufacturing.

Responsibilities

• Own features end-to-end across system design, implementation, testing, observability, deployment, and lifecycle support
• Support platform enablement and architecture decisions through code reviews and shared engineering standards
• Design, build, test, deploy, and operate full stack software solutions
• Collaborate with business teams to translate requirements into scalable solutions
• Build and implement Custom AI Agents for workflows such as task automation, decision support, summarization, multi-step reasoning, and guided execution
• Demonstrate engineering proficiency using Vibe Coding prototypes in a timely development process
• Integrate systems using Model Context Protocol (MCP) to enable structured context sharing between models, tools, and agents
• Expose tools and capabilities to LLM-based agents and enable interoperability across AI components without hard-coded integrations
• Integrate applications with external and internal AI services including LLMs, embeddings, search, and tools via well-designed APIs
• Harden AI components for 24x7 critical physical manufacturing systems with focus on reliability, resiliency, latency, performance, security, permissions, data boundaries, observability, and maintainability
• Apply retrieval-augmented generation (RAG) systems within production environments
• Use AI-assisted development tools (code generation, refactoring, test creation, documentation), and critically evaluate and refine AI-generated output with human judgment
• Conduct requirements gathering and analysis for software domains, interfaces, and characteristics
• Write code using programming, scripting, and database languages; support testing, deployment, maintenance, and evolution
• Follow guidelines for coding standards, code reviews, source control, build processes, testing, and operations

Requirements

• Strong full stack software engineering foundation including object-oriented design, clean code, testing strategies, and long-term maintainability
• Experience building and operating production-grade backend or full-stack systems, including API design, service integration, and data persistence
• Ability to design and evolve scalable system architectures with tradeoffs across performance, reliability, security, and developer productivity
• Experience in cloud-native environments including CI/CD pipelines, containerized deployments, and modern operational practices
• Solid understanding of data modeling and storage across relational and non-relational technologies, including selecting the right tool
• Track record of owning software end-to-end from design through lifecycle support, collaborating across engineering and business teams
• Experience with C#, ASP.NET, Angular, RESTful APIs, SQL and NoSQL databases, and Kubernetes-based platforms
• Experience designing and implementing custom AI agents beyond simple chat interfaces
• AI-native skills including prompt engineering, Vibe Coding, context window management, and chain-of-thought design
• Experience integrating systems using MCP or equivalent structured agent/tool interfaces, including prompt design and tool invocation
• Ability to reason about hallucination risk, failure modes, permissions, and guardrails in AI-enabled systems, plus hands-on RAG integration experience

Preferred Qualifications

• Experience applying AI-enabled development practices to accelerate engineering workflows and improve productivity
• Ability to critically evaluate AI-generated outputs and refine them for production-grade systems
• Experience building interoperable AI systems without hard-coded integrations
• Strong understanding of operationalizing AI in critical environments with high reliability and performance requirements

Kubernetes / Platform Engineering

• Strong interest in Kubernetes and cloud-native infrastructure, including running, upgrading, and troubleshooting production clusters
• Desire to deepen expertise in container orchestration, GPU workloads, and platform reliability
• Experience designing and running distributed systems on Kubernetes
• Understanding of message-driven architectures, horizontal scaling, fault tolerance, and multi-tenant workloads
• Help shape a platform roadmap for processing large volumes of data across sites

Technologies

• C#, ASP.NET, Angular
• RESTful APIs
• SQL, NoSQL
• Kubernetes
• CI/CD pipelines, containerized deployments
• Model Context Protocol (MCP)
• LLMs, embeddings, search
• Retrieval-augmented generation (RAG)
• Prompt engineering, Vibe Coding, context window management, chain-of-thought design