AI Platform SRE: Build Reliable LLM Infra & Cost Opt

Doist; Amsterdam; Hybrid; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Hybrid onboarding

Relocation support

Health insurance

Professional development budget

Flexible benefits

In-office perks with meals

Job summary

Manychat is seeking an AI-native SRE to own the reliability, performance, and cost of our AI infrastructure. You will ensure production-grade availability across AI gateway, inference services, and cloud provider integrations, shaping standards and roadmaps for a fast-growing platform.

You’ll collaborate with the Head of Infrastructure, enjoy autonomy, and influence architecture choices across teams. Strong focus on SLOs, observability, and cost control will be key to success.

Qualifications

• 5+ years in SRE / platform / infrastructure engineering with production ownership at scale.
• Experience operating LLM-backed systems in production with provider APIs (Bedrock/OpenAI/Anthropic).
• Strong cloud-native background (AWS, Kubernetes, Terraform/IaC, CI/CD).
• Proven observability practice and ability to define SLOs for non-deterministic systems.
• Track record of cost-optimization and making cloud spend visible.

Responsibilities

• Own reliability and performance of AI infrastructure (AI Gateway, inference services, provider integrations).
• Design and evolve the AI Gateway (routing, failover, rate limiting, caching, guardrails).
• Build observability: latency, throughput, error SLOs, token metrics, drift signals.

Skills

SRE

Platform engineering

Cloud-native

Observability

Cost optimization

Tools

AWS

Kubernetes

Terraform/IaC

Job description

Manychat is seeking an AI-native SRE to own the reliability, performance, and cost of our AI infrastructure. You will ensure production-grade availability across AI gateway, inference services, and cloud provider integrations, shaping standards and roadmaps for a fast-growing platform.

You’ll collaborate with the Head of Infrastructure, enjoy autonomy, and influence architecture choices across teams. Strong focus on SLOs, observability, and cost control will be key to success.