Senior Site Reliability Engineer
Core
Define SLOs, error budgets, and observability for agent APIs, streaming, and background work while managing AWS infrastructure and AI model resilience.
Role type
Senior Site Reliability Engineer (AI/ML Infrastructure)
Builds
AWS infrastructure (ECS, Aurora, Redis, Bedrock), observability pipelines, and resilient model-layer systems.
Domain
Cloud Infrastructure & Artificial Intelligence
Deliverable
production ML models
Required skills
AWS (ECS, Fargate, Aurora, Bedrock), Terraform, PostgreSQL operations, SLO/observability (Datadog, OpenTelemetry), incident response, production coding, multi-tenant security
Preferred skills
LLM/AI workload experience, AI-agent automation, SOC 2/PCI DSS, policy as code, multi-region data-residency
Technologies
AWS, Terraform, Spacelift, Datadog, Coralogix, OpenTelemetry, PostgreSQL, Amazon Bedrock
Responsibilities
Define SLOs and error budgets for agent APIs; manage AWS infrastructure and database resilience; build model-layer resilience and guardrails; lead incident response and on-call; optimize cloud and model spend.
Seniority
Senior, hands-on IC