Senior Site Reliability Engineer
Core
Own the reliability, observability, and infrastructure for a multi-tenant AI agent platform serving thousands of businesses.
Role type
Senior Site Reliability Engineer (AI/ML Infrastructure)
Builds
Shared agent runtime, model gateway, retrieval, guardrails, evaluations, and cost controls for AI capabilities.
Domain
Cloud Infrastructure (AWS) + Artificial Intelligence (LLMs/Agents)
Deliverable
production ML models
Required skills
AWS (ECS, Aurora, Redis, Bedrock), Terraform, SLO definition, Observability (Datadog, OpenTelemetry), PostgreSQL operations, Incident response, Multi-tenant security, Cost optimization
Preferred skills
LLM workload experience, AI agent automation, Regulated environments (SOC 2, PCI DSS), Multi-region data residency
Technologies
AWS, Terraform, Spacelift, Datadog, Coralogix, OpenTelemetry, GitHub Actions, PostgreSQL, Amazon Bedrock
Responsibilities
Define SLOs and error budgets for agent APIs; Own AWS infrastructure and IaC; Build observability for AI signals; Ensure data store resilience; Build resilience into the model layer; Protect platform with multi-tenant quotas and circuit breakers; Partner with Security on AI risks; Set guardrails for AI agents; Lead incident response and game days; Track and reduce cloud and model spend.
Seniority
Senior, hands-on IC
