Full Stack AI Engineer

Micron Technology•Boise, ID

About The Position

Micron Technology is seeking an AI-centric Full Stack Software Engineer to design, build, and support modern software solutions, focusing on AI-enabled applications and intelligent automation. The role applies prompt engineering, Vibe Coding, rework-rate reduction, custom agents, and Model Context Protocol (MCP) integrations alongside strong software engineering fundamentals to operationalize AI capabilities in production systems. The engineer will be accountable for full-stack solutions that shorten development and feedback cycles, automate routine engineering work, augment human decision-making, and embed intelligence into development workflows and delivered applications. The team builds scalable, cloud-native software platforms for critical manufacturing and business operations. It uses modern full-stack engineering practices and AI-driven technologies to improve automation, decision-making, and operational efficiency. AI components must be hardened for 24x7 critical physical manufacturing systems, with attention to reliability, resiliency, latency, performance, security, permissions, data boundaries, observability, and maintainability. Micron describes benefits including medical, dental, and vision plans, income-protection programs for illness or injury, paid family leave, paid time off, and paid holidays.

Requirements

Bachelor's degree in Computer Science, Software Engineering, Information Systems, or a related technical field.
At least 3 years of experience developing production-grade full-stack or backend software applications, including API design, service integration, and data persistence.
Hands-on experience with cloud-native technologies, CI/CD pipelines, containerization, and Kubernetes-based deployments.
Experience with relational and NoSQL databases, including data modeling and storage architecture design.
Experience designing, developing, and deploying AI-enabled applications, including custom AI agents and RAG-based systems.
Experience with prompt engineering and Vibe Coding prototypes, AI tool integration, and evaluating AI-system reliability, security, and failure modes.

Nice To Haves

At least 7 years of experience building enterprise-scale distributed applications in cloud environments.
Experience building and integrating Model Context Protocol (MCP) for structured context sharing between models, tools, and agents; exposing tools and capabilities to LLM-based agents; and enabling interoperability across AI components without hard-coded integrations.
Proficiency with modern technology stacks such as C#, ASP.NET, Angular, SQL, NoSQL, and Kubernetes.
Experience developing AI agent skills, tool invocation frameworks, and multi-agent workflow solutions.
Strong understanding of prompt engineering, context-window management, chain-of-thought design, and AI workflow optimization.
Experience architecting highly available, critical systems with a focus on performance, resiliency, observability, and security.
Track record of leading architecture discussions, conducting code reviews, and establishing engineering standards and guidelines.

Responsibilities

Design, develop, test, deploy, and maintain scalable full-stack applications and platform services.
Own software solutions end-to-end, including system design, architecture, implementation, testing, observability, deployment, and lifecycle support.
Develop and implement custom AI agents for workflow automation, decision support, summarization, and multi-step reasoning.
Integrate AI services, large language models, embeddings, search technologies, and external tools through secure, scalable APIs.
Build and maintain MCP-based integrations for structured communication between AI models, tools, and business systems.
Collaborate with engineering, product, and business stakeholders to translate requirements into reliable, maintainable, scalable solutions.
Apply AI-assisted development practices while ensuring code quality, architectural integrity, security, reliability, and long-term maintainability.
Harden AI components for 24x7 critical physical manufacturing systems, considering reliability, resiliency, latency, performance, security, permissions, data boundaries, observability, and maintainability.