Principal, Agentic Reliability Engineer

Agentic Reliability Engineer (ARE)
Slalom
· Agentic Managed Services
· Remote (US) with possible client travel
· Principal or Senior Principal level ABOUT

THE ROLE AI agents are moving into production faster than most organizations can operate them reliably and closing that gap is exactly why Slalom built its Agentic Managed Services (AMS) practice. As an Agentic Reliability Engineer, you are the technical heart of that work: the engineer who makes AI agents dependable in the real world.

Where a traditional Site Reliability Engineer keeps software services healthy, you own the reliability of AI agents. These are systems that reason, make decisions, and act on a client's behalf, but can fail in ways classical engineering never had to consider. You'll help design and stand up agentic solutions with clients, prove they hold up under real conditions, and then keep them performing in production: watching how they behave, diagnosing why they drift, tuning and evaluating them, and safely rolling out changes as they evolve.

Your day to day will look like a small senior delivery pod working shoulder-to-shoulder with the client and with Slalom's platform team. It's a collaborative, high-ownership environment: you are the final technical authority on how the agents behave, and the person a client trusts to tell them their systems are reliable, well-governed, and getting better over time. Because our agentic reliability engineering group is a new and fast-growing practice, you'll also help shape how the work is done.

We expect you to provide input in to the patterns, tooling, and standards that make running production agents repeatable.

This is a role for engineers who want to be at the frontier of what AI systems actually do in production. You thrive on work with real stakeholders, measured outcomes, and sustained impacts. WHAT YOU'LL DODesign & deploy agentic solutions
* Partner with clients to shape the opportunity and design the agent workflow — what the agents should do, how their performance will be judged, and what guardrails keep them safe.
* Build the first working agents: stand up the initial workflow, evaluation harness, and guardrails, and demonstrate that the solution meets the client's acceptance criteria under real conditions.
* Define the reliability baseline the solution must hold in production including the SLOs, evaluation criteria, and autonomy posture that govern it.

Run & continuously improve production agents
* Own root-cause analysis and ongoing performance of the agent workflow itself: why it behaves as it does, and how to make it measurably better over time.
* Own the evaluation harness: configure, run, and interpret agent evaluations against workflow-specific acceptance criteria.
* Monitor drift signals (e.g. output-quality degradation, latency trends, evaluation pass-rate decline, cost anomalies) and remediate before they breach SLOs.
* Run A/B and shadow evaluations when agent behavior changes are proposed
* Capture operational findings, incident lessons, and evaluation-calibration notes so the pod's knowledge compounds over time rather than resetting.

Measure, analyze & communicate performance
* Define and track the KPIs that describe how well the agents are performing and investigate when they move in unexpected directions.
* Translate telemetry into narratives the team and client can act on.
* Develop and communicate clear plans to improve agent performance and reporting on their impact once shipped.
* Serve as the final technical authority for AI agent incidents including owning root-cause analysis of the agent workflow, remediation, and postmortem documentation.
* Determine whether an incident reflects a transient error, agent drift, workflow-logic failure, or an underlying…