Senior Site Reliability Engineer, Agentic Automation

SewerAI Corporation
•$150,000 - $190,000•Remote

About The Position

SewerAI is hiring a senior engineer to bring AI agents into company workflows. The role identifies repetitive manual work across engineering and other teams, then builds agentic workflows to reduce that work and enable new capabilities. The engineer also owns the internal platform that runs these agents, ensuring it is reliable, observable, and secure. The position combines SRE, automation, and applied AI. It calls for an operator’s mindset, solid coding ability, sound judgment about when agents are appropriate, and the ability to learn how different teams work. This is a remote role on the SRE team and is not part of the on-call rotation.

Requirements

  • Hands-on experience building and running agentic or LLM-powered workflows in a real environment, not just prototypes.
  • Strong Python or TypeScript scripting skills, including API integrations and glue code, and the ability to read and modify production code.
  • Solid working knowledge of AWS and cloud security fundamentals.
  • Experience with Terraform, OpenTofu, or a similar infrastructure-as-code tool.
  • Experience building and maintaining automated CI/CD pipelines; GitHub Actions is preferred.
  • At least 6 years of experience in SRE, DevOps, infrastructure, or platform engineering.
  • An operator’s mindset, including consideration of how workflows fail in production.
  • Sound judgment about when to use an agent, a cron job, or no automation.
  • Strong communication skills, including the ability to understand other teams’ work, identify bottlenecks, and explain tradeoffs in plain language.
  • Strong organizational skills to prioritize requests, update stakeholders, and see projects through to adoption.
  • Comfort turning vague pain points into concrete automations, including in unfamiliar areas.

Nice To Haves

  • Experience with agent and LLM risks such as prompt injection, data exfiltration, and over-privileged tools, as well as secrets management, IAM, sandboxing, or isolation.
  • Familiarity with the day-to-day work of teams such as sales, finance, customer success, or operations.
  • Experience with Temporal.io or similar workflow orchestration.
  • Experience with LLM evaluation frameworks and observability tooling.
  • Experience with Claude Code, MCP, and integrations with tools such as Slack, Linear, and Notion.
  • Experience in infrastructure, utility, or geospatial domains.

Responsibilities

  • Work with engineering, operations, customer success, finance, and other teams to identify high-value automation opportunities and build and ship agentic workflows.
  • Automate SRE and engineering chores, including alert triage, ticket creation and routing, incident follow-ups, dependency updates, and CI maintenance.
  • Build tools that non-technical teams can use without needing to understand their implementation.
  • Operate the internal agent platform, including sandboxed execution, secrets management, network egress controls, permissions, and cost controls.
  • Support agent workflows with evaluations, observability, alerting, runbooks, and clearly defined failure modes.
  • Define agent access and action guardrails, including least privilege, human approval for risky actions, and audit trails.
  • Document patterns and build reusable components so others can safely create agent workflows.
  • Measure workflow impact, including hours saved, response times, and adoption, and retire workflows that do not provide value.
  • Prioritize requests from across the company, keep stakeholders updated, and carry projects through to adoption.

Benefits

  • Medical, dental, vision, and basic life benefits.
  • 401(k).
  • Unlimited PTO.
  • Tools and resources to support success.
  • Competitive compensation with high-growth potential.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service