Staff AI Platform SRE — Reliable LLM Infra & FinOps

Academic Key; Amsterdam; Hybrid; EUR 110,000 - 145,000; Full time

Benefits offered by this job

Hybrid onboarding

Relocation support

Health insurance

Professional development budget

Flexible benefits

Hybrid work

Free meals and snacks

Annual offsites

Job summary

Manychat in Amsterdam, Netherlands seeks a Staff Site Reliability Engineer to own the reliability, performance, and cost of our AI platform infrastructure, including AI Gateway and inference services. You’ll work on deploying resilient, scalable systems with LLM integrations.

You will shape SRE practices at scale, design observability, drive FinOps, and mentor teams as we expand AI features with providers like Bedrock and OpenAI.

Qualifications

• 5+ years in SRE / platform / infra engineering.
• Production ownership at scale with AI/LLM workloads.
• Hands-on with cloud-native tech: AWS, Kubernetes, Terraform.
• Strong observability and SLO definition.
• Cost optimization and FinOps experience.

Responsibilities

• Own reliability and performance of AI infrastructure including AI Gateway and inference services.
• Integrate with Bedrock, Azure OpenAI and other providers.
• Design and evolve AI Gateway routing, failover, rate limiting, caching, guardrails.
• Build observability: latency/throughput/error SLOs per model/provider; token metrics.
• Drive cost optimization and FinOps for AI workloads.
• Run capacity planning and incident response; write runbooks and postmortems.
• Scale AI expertise across the org; set standards and coach teams.

Skills

Site reliability

Cloud-native

AWS

Kubernetes

Terraform IaC

Observability

Cost optimization

Tools

Prometheus

Grafana

OpenTelemetry

LLM providers

AWS

Job description

Manychat in Amsterdam, Netherlands seeks a Staff Site Reliability Engineer to own the reliability, performance, and cost of our AI platform infrastructure, including AI Gateway and inference services. You’ll work on deploying resilient, scalable systems with LLM integrations.

You will shape SRE practices at scale, design observability, drive FinOps, and mentor teams as we expand AI features with providers like Bedrock and OpenAI.