Xplor
Skills: SQL, AWS, CI/CD
About the opportunity
AI Engineering builds the shared agent platform behind Xplor(https://himalayas.app/companies/ourxplor)'s AI capabilities: the agent runtime, model gateway, retrieval, guardrails, evaluations, and cost controls. We build the hard parts once, so every product team can ship AI features faster and safely.
We're looking for a hands-on Site Reliability Engineer to own how our agent platform behaves in production. AI workloads bring new reliability problems: long streaming responses, background agents, model-provider quotas, outputs that can fail silently, agents that take real actions, and spend that grow with usage. You'll treat them as first-class engineering problems. As AI agents take on more of our operational work, you'll decide what they're allowed to do and make sure they do it safely.
Why this role is exciting
Reliability for a new kind of workload. The playbook for running AI agents in production is still being written, and you'll help write it. Scale with real stakes. A multi-tenant platform serving thousands of businesses, and AI features they depend on to run their day. Greenfield foundations. Define the SLOs, alerting, game days, agent guardrails, and standard deployment paths that every product team will build on. Cost is an engineering problem. Token economics, model routing and cost per task matter as much as uptime. AI-native operations. Use AI agents to automate toil, speed up investigations and improve infrastructure code; with the approval gates, scoped permissions and audit trails that make it safe.
What you’ll do
Define SLOs and error budgets for agent APIs, streaming and background work, including quality signals like task success, tool-call failures and evaluation regressions, and alert on what matters to customers. Own the platform's AWS infrastructure (ECS on Fargate, Aurora PostgreSQL, Redis and Amazon Bedrock) as Terraform delivered through Spacelift. Build observability in Datadog and Coralogix wit …truncated… e may record vid…
Sign in to see the original posting
Browse more developer jobs on RoleBurst