Senior Agentic Operations Engineer

Arizona State University•Scottsdale, AZ

2d•Hybrid

About The Position

Enterprise Technology is building a new Agentic Operations team and is hiring two Senior Agentic Operations Engineers to help build this capability from the ground up. The team will develop and manage AI agents that monitor university systems, identify potential issues, and help resolve problems before they impact the ASU community. As a member of this new team, you will help establish the tools, processes, and safeguards needed to use AI safely and effectively within ASU’s technology environment. You will work across monitoring, automation, security, and AI-driven remediation, with a focus on building reliable and well-governed solutions. This is an opportunity to shape a new capability at ASU. We are looking for experienced engineers who are comfortable with change, learn quickly, and enjoy solving complex problems. As the platform matures, you will help expand the ways AI can safely support university operations.

Requirements

Bachelor's degree and five (5) years of experience appropriate to the area of assignment/field; OR, Any equivalent combination of experience and/or training from which comparable knowledge, skills and abilities have been achieved.
Strong programming skills in Python (async, typing, testing).
Cloud infrastructure experience (AWS preferred) and infrastructure as code (OpenTofu/Terraform).
Experience with observability and telemetry (metrics, logs, traces); familiarity with Datadog a plus.
Experience in one or more of: time-series/anomaly detection or baseline modeling; or secure automation, IAM/RBAC, and safe automated remediation with rollback.
Familiarity with SRE practices — SLOs, error budgets, incident management, on-call.
Comfort operating in an ambiguous, discovery-oriented environment and helping define new practices.
Demonstrated ability to model empathy, compassion, and emotional intelligence.
Experience in a values-driven organization with a strong commitment to inclusion and belonging.
Ability to cultivate a psychologically safe environment where all team members can thrive.
Applicants must be eligible to work in the United States.

Nice To Haves

Hands-on experience with LLMs and/or agent-based systems and their operational risks.
Familiarity with Datadog a plus.

Responsibilities

Help build, deploy, and govern a platform of AI agents that monitor ASU's environment and, over time, help remediate issues safely.
Contribute to the discovery and definition of the team's tooling, practices, standards, and operating model as a new group.
Work across telemetry and detection (ingesting signals, modeling baseline health, tuning anomaly detection) and orchestration and remediation (secure execution, IAM/RBAC, human-audited runbooks, failsafe rollbacks), developing deeper emphasis in one area over time.
Uphold and help define governance standards: role-based access control, audit logging, human-in-the-loop escalation, and reversible/rate-limited actions.
Sequence automation responsibly up an autonomy ladder — starting with low-risk, reversible actions on low-blast-radius systems and earning broader autonomy as trust is proven.
Serve as a peer reviewer for the other engineer's agent logic before any production deployment.
Partner with system owners, security, and other teams to adopt agents safely across the environment.
Leverage AI in routine tasks and contribute ideas for using AI to improve the unit's efficiency and overall performance.
Take responsibility for fostering a positive culture, upholding organizational values, and championing engagement in all its forms.
Collaborate across teams and actively participate in ET/ASU events and programs.