AI Enabled Full Stack Engineer
Micron Technology
- Location
- Taoyuan - Fab 11, Taiwan
- Work model
- On-Site
- Level
- Mid
- H-1B history
- 69 approvals (FY2023)
- Posted
- 3h ago
Skills
About this role
Our vision is to transform how the world uses information to enrich life for all . Micron Technology is a world leader in innovating memory and storage solutions that accelerate the transformation of information into intelligence, inspiring the world to learn, communicate and advance faster than ever. As a Senior AI Full Stack Engineer, you will be responsible for designing, developing, deploying, and supporting AI-enabled applications and enterprise solutions across the full technology stack. You will collaborate closely with business partners, product teams, and fellow engineers to translate business needs into scalable, reliable, and maintainable solutions while advancing the adoption of AI-enabled software engineering practices. Responsibilities include, but are not limited to: Design, build, test, deploy, and operate full-stack software solutions supporting business and manufacturing operations. Own solutions end-to-end, including system architecture, implementation, testing, observability, deployment, operational support, and lifecycle management. Collaborate with business stakeholders to gather requirements and translate them into scalable technical solutions. Contribute to platform enablement, architecture decisions, code reviews, and engineering best practices. Design and implement custom AI agents to automate tasks, orchestrate workflows, provide decision support, enable summarization capabilities, and perform multi-step reasoning. Build and integrate systems using Model Context Protocol (MCP) to enable structured interactions between AI models, tools, agents, and enterprise systems. Develop and integrate AI-powered solutions utilizing Large Language Models (LLMs), enterprise search, embeddings, APIs, and Retrieval-Augmented Generation (RAG) architectures. Apply AI-assisted development practices to accelerate software development, testing, documentation, code modernization, and overall engineering productivity. Ensure AI-enabled systems meet enterprise requirements for reliability, resiliency, security, performance, observability, maintainability, and data protection. Partner with cross-functional teams to deploy solutions into mission-critical manufacturing environments and provide ongoing operational support. Participate in a rotating 24x7 on-call support model and provide timely response and resolution for production incidents impacting critical business and manufacturing operations. Demonstrate Micron's core values of People, Innovation, Tenacity, Collaboration, and Customer Focus in all aspects of work.
Required Qualifications
Strong foundation in full-stack software engineering fundamentals, including object-oriented design, clean code practices, testing strategies, and long-term maintainability. Proven experience developing, deploying, and supporting production-grade software systems. Experience with backend services, API development, service integrations, and data persistence technologies. Strong understanding of scalable system architecture, application performance, reliability, and operational excellence. Experience working in cloud-native environments, CI/CD pipelines, containerized deployments, Kubernetes platforms, and modern DevOps practices. Experience working with relational and non-relational databases and modern data storage technologies. Ability to work independently while collaborating effectively across engineering, product, and business teams. Strong problem-solving skills and the ability to balance innovation with operational reliability.
Preferred Qualifications
Experience designing and implementing custom AI agents beyond traditional chatbot solutions. Practical experience with Prompt Engineering, Context Window Management, Tool Invocation, Agent Skills, and AI-assisted development practices. Experience integrating systems using Model Context Protocol (MCP) or equivalent structured agent and tool frameworks. Experience building and operationalizing Retrieval-Augmented Generation (RAG)