SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
PagerDuty is seeking a Forward Deployed Engineer to join the SRE Agent team, working embedded within the company's largest customer accounts. In this role, you will connect PagerDuty's AI-powered SRE Agent to production environments—including observability tools, infrastructure-as-code platforms, GitOps tooling, and CI/CD pipelines—while guiding customer teams from AI-assisted incident response to supervised and autonomous operations with safety guardrails.
You will split your time between customer sites and the London office, working with 2–4 strategic accounts simultaneously. Key responsibilities include:
• Embedding and driving SRE Agent adoption by deploying the platform, configuring connectors, and embedding AI actions across the incident management lifecycle to maximize customer value.
• Building and contributing core agent capabilities: scoping, designing, and shipping reusable agent tools, connectors, and skills through the product team's repos and evaluation gates.
• Running pilots and unblocking adoption by standing up new agentic capabilities with strategic accounts first, gathering evaluation data, identifying technical blockers (permissions, telemetry, missing connectors), and building production fixes directly into the product.
• Integrating with production stacks and progressive delivery patterns by connecting the SRE Agent to Terraform/Pulumi, ArgoCD, CI/CD pipelines, and observability platforms, guiding customers safely from AI-assisted to autonomous operations.
• Setting technical direction and providing feedback by defining 3–6 month technical roadmaps across assigned accounts, offering architectural guidance to product and engineering managers, and bringing customer friction and evaluation data back to the core team.
This is a Staff-level individual contributor role on the product engineering team, offering the opportunity to directly shape how agentic AI operates within strategic Fortune 100/500 customers. The ideal candidate brings strong software engineering fundamentals, hands-on production experience with LLM and agentic systems, and the customer-facing skills to bridge technical execution with business strategy.
**REQUIREMENTS**
Basic Qualifications:
• 8+ years of experience building and shipping production software across team boundaries (assessed against PagerDuty Staff Engineer / SDE V expectations)
• Hands-on experience with LLM and agent systems in production, including agent development, tool-use frameworks (MCP or equivalent), evaluation pipelines, and guardrail design
• Customer-facing skills: ability to run technical design sessions with customer engineers and present business cases to their leadership
• Comfort with ambiguity: ability to start from vague problem statements in unfamiliar environments and reach working software with minimal direction (founders and founding engineers often excel here)
• Proven track record of shipping software that achieved adoption, with sound judgment about which customer requests generalize and when not to build
• Infrastructure & Deployment expertise: demonstrated experience with Terraform or Pulumi at scale, GitOps (ArgoCD or equivalent), CI/CD pipeline design, and progressive delivery patterns (canary, blue/green, soak periods)
• Willingness to travel 25–50% during active customer engagements
Preferred Qualifications:
• Practical operational knowledge of incident management and observability concepts (on-call, postmortems, SLOs/SLIs, alerting)
• Customer-facing technical consulting, forward-deployed engineering, or solutions architecture experience built on a core software engineering foundation
• Background as a founder or founding engineer accustomed to high ambiguity and unscripted problem-solving
• Experience with policy-as-code, fine-grained permissioning, or safety guardrail patterns for agent-driven automation
• Production experience with PagerDuty or competing digital operations and incident management platforms
• Active open-source contributions to the AI agent or Model Context Protocol (MCP) ecosystem
