SRE - Senior Site Reliability Engineer

The role

Help make AI agents reliable enough to run business-critical workflows.

Our platform enables AI agents to execute complex customer workflows through reasoning and extensive tool use. As a Senior Site Reliability Engineer, you’ll shape how we build, observe, release, and operate these systems—and help earn the trust of customers who depend on them.

This is a hands-on engineering role with scope to build and evolve our reliability practice. You’ll work across infrastructure and application teams, improving the foundations that allow engineers to ship quickly and safely.

You’ll tackle two connected challenges: keeping a fast-moving engineering environment reliable as AI accelerates code delivery, and understanding how agents behave in production. That means detecting failures early, investigating unexpected behaviour, and identifying what drives latency across complex workflows.

What you’ll do

• Shape our reliability foundations. Evolve our infrastructure, observability, and release processes to support rapid development and dependable production systems.

• Make agent behaviour visible. Build telemetry that helps teams understand workflow execution, spot misbehaving agents, and investigate failures and latency.

• Improve detection and recovery. Create actionable monitoring, alerts, and diagnostic tools so on-call engineers can assess customer impact and mitigate incidents quickly.

• Lead incident response and follow-through. Coordinate structured responses, investigate root causes, and work with engineering teams to deliver post-incident actions that prevent recurrence.

• Build secure infrastructure. Strengthen tenant isolation, sandboxed execution, encryption key management, and network protections for enterprise workloads.

• Automate operational work. Improve infrastructure as code, CI/CD, and container orchestration to reduce repetitive work and make changes safer.

• Own reliability improvements end to end. Identify priorities, propose solutions, deliver them to production, and measure their impact.

• Make pragmatic trade-offs. Balance reliability, security, delivery speed, and operational complexity, including during incidents when information is incomplete.

What you’ll bring

We’ll assess candidates against the following core capabilities:

• Production experience with distributed systems. You’ve designed and operated systems at scale and understand failure modes, capacity planning, and the trade-offs between consistency, availability, and latency.

• Strong observability and incident response skills. You build monitoring that surfaces meaningful problems, lead methodical investigations, and turn incidents into lasting improvements.

• A security-first engineering mindset. You can reason about sensitive data, access boundaries, encryption, and workload isolation, and translate those concerns into practical infrastructure controls.

• Infrastructure automation experience. You’ve used infrastructure as code, CI/CD pipelines, and container orchestration in production. You know when to automate and when a clear, tested runbook is the right tool.

• Hands-on ownership. You take projects from identifying a problem through to deployment and ongoing operation, collaborating across teams to deliver measurable results.

• Sound engineering judgement. You can prioritise the work that matters most, explain trade-offs clearly, and make considered decisions under pressure.

Experience that would help

These are useful additions, rather than requirements:

• GCP, Kubernetes, or comparable cloud-native infrastructure.

• Sandboxed execution environments and multi-tenant workload isolation.

• AI/ML systems in production, particularly the reliability challenges of LLM-based applications.

• Product engineering, with an understanding of application development and the developer experience.

What to expect

You’ll help build the reliability practice, with the autonomy and responsibility to influence how engineering teams work. The role suits someone who enjoys writing code, improving systems, and bringing structure to operational challenges.

Your primary focus will be the reliability, security, and operability of the platform and its agents. You’ll work closely with the teams building AI capabilities and customer-facing features.

Our tech stack

• Cloud: GCP—Cloud Run, GKE, and GCS

• Infrastructure: Terraform and Docker

• Observability: Datadog

• Services: TypeScript and Python

• Data: Postgres and Redis

You’ll read and occasionally modify application code to diagnose issues and improve reliability. Deep expertise in both TypeScript and Python isn’t required.