Applied AI/Automation Engineer

For over four decades, Cirrus Logic has been propelled by the top engineers in mixed-signal processing. Our rockstar team thrives on solving complex challenges with innovative end-user solutions for the world's top consumer brands. Cirrus Logic is also known for its award-winning culture, which was built on a foundation of inclusion and fairness, meaningful community engagement, and delivering enjoyable employee experiences at every turn. But we couldn’t do it without our extraordinary workforce – and that’s where you come in. Join our team and help us continue to make Cirrus Logic an exceptional place to grow your career!

Our Customer Enablement organization defines semiconductor system requirements, develops technical documentation, and supports internal teams and customers in using our devices.

We are seeking an Applied AI/Automation Engineer to design, build, deploy, and support practical AI solutions that improve internal engineering workflows, automate repetitive tasks, and make technical information easier to find and use. This role will apply the latest AI techniques within scalable software solutions, helping move promising ideas from experimentation into reliable, maintainable tools that deliver measurable value. The role will involve designing solutions that are secure, measurable, maintainable, and useful in people’s daily work.

This role will also contribute to the development of documentation and information tools, scripts, and utilities. We eagerly pursue scripting, data modeling, and process automation to operate more efficiently in collaboration with work partner teams.

The ideal candidate combines strong software engineering skills with hands-on experience building AI-enabled applications.

Depending on business priorities, initiatives may include:

Building LLM-powered assistants and copilots

Creating AI agents and tool-integrated workflows that connect to enterprise systems

Automating repetitive engineering and operational tasks

Applying document intelligence, extraction, classification, and summarization

Developing internal developer-productivity tools

Designing evaluation methods, quality metrics, monitoring, and feedback loops

Improving prompts, workflows, context retrieval, model selection, performance, and cost

Establishing secure deployment patterns, access controls, and responsible AI practices

Success in this role means delivering AI capabilities that are useful, trusted, adopted, and sustainable in production while helping engineering teams use AI efficiently and effectively.