AI Automation & Tools Engineer

Saige Partners•San Jose, CA

1d•Onsite

About The Position

We are seeking an experienced AI Automation & Tools Engineer to support the continued advancement of automation and tooling initiatives across the Eldora, Deus/Euclid, and Elroy projects. This role will focus on developing scalable AI-driven automation solutions that improve system efficiency, streamline defect triage, and enhance overall engineering productivity within complex hardware-software validation environments. The ideal candidate will bring strong Python development skills, hands-on automation experience, and a background in storage firmware validation or related system-level environments.

Requirements

Strong proficiency in Python programming.
Hands-on experience developing and maintaining automation frameworks.
Experience working in NVMe/storage firmware validation or similar hardware-software integrated environments.
Experience with log analysis, protocol analyzers, and trace diagnostics tools (including Beagle trace analysis).
Strong analytical and problem-solving skills with the ability to troubleshoot complex systems.
Understanding of automated triage methodologies and workflow optimization techniques.

Nice To Haves

Experience applying AI and machine learning technologies to automation and validation processes.
Familiarity with advanced diagnostic and debugging tools.
Strong written and verbal communication skills.
Ability to collaborate effectively within cross-functional engineering teams.

Responsibilities

Design and implement AI-powered automation workflows to support validation and testing operations.
Develop and deploy intelligent automation agents to accelerate issue detection, analysis, and resolution.
Create scalable automation frameworks that reduce manual intervention and improve operational efficiency.
Establish automated “First Level of Defense” triage systems to manage initial failure analysis.
Implement automated setup-health checks, sideband diagnostics, and Beagle trace pre-screening processes.
Resolve recurring or routine issues through automation before escalation to full-time engineering teams.
Streamline issue identification and defect discovery workflows across multiple toolsets and validation environments.
Improve Mean Time to Resolve (MTTR) by automating diagnostic and routing processes.
Perform log analysis and trace diagnostics to identify system failures and optimization opportunities.
Reduce repetitive manual triage tasks and known setup issue investigations through automation.
Enable core engineering teams to focus on high-priority architecture initiatives and critical project milestones.
Build scalable workflows capable of supporting increased test volumes across Elroy and Eldora programs without additional permanent headcount.