Staff Site Reliability Engineer (AI)

TL;DR

Staff Site Reliability Engineer (AI): Designing and optimizing the reliability, performance, and cost of a scalable AI platform with an accent on AI Gateway architecture and LLM provider integrations. Focus on building observability for non-deterministic systems, managing inference latency, and implementing FinOps strategies for AI workloads.

Location: Hybrid in Amsterdam, Netherlands. Relocation support for the employee and their family is provided.

Company

hirify.global provides AI-powered automation tools for creators and brands to engage audiences across social platforms like Instagram, Messenger, and WhatsApp.

What you will do

• Own the reliability and performance of AI infrastructure, including AI Gateway and integrations with Amazon Bedrock and Azure OpenAI.
• Design and evolve the AI Gateway's routing, failover, rate limiting, caching, and guardrails.
• Build observability for AI systems, defining SLOs for latency, throughput, and quality per model and provider.
• Drive FinOps and cost optimization for AI workloads through model right-sizing and caching strategies.
• Manage capacity planning and incident response for inference services, including runbooks and postmortems.
• Scale AI expertise across the organization by setting technical standards and coaching teams on LLM features.

Requirements

• 5+ years of experience in SRE, platform, or infrastructure engineering at significant scale.
• Hands-on experience operating LLM-backed systems in production (e.g., OpenAI, Anthropic, Bedrock).
• Deep cloud-native background with AWS, Kubernetes, Terraform/IaC, and CI/CD.
• Strong observability practice using Prometheus, Grafana, or OpenTelemetry.
• Proven track record of implementing cloud and inference cost-optimization.
• Must be based in or be able to relocate to the Netherlands.

Nice to have

• Experience building or operating LLM gateways/proxies such as LiteLLM or Kong AI Gateway.
• Experience with GPU workload optimization, quantization, or serving frameworks (vLLM, TGI, Triton).
• Experience with evaluation pipelines and quality monitoring for LLM outputs.

Culture & Benefits

• Relocation support for you and your family.
• Comprehensive health insurance and a flexible benefits budget for wellbeing and home office.
• Professional development budget for conference tickets and online courses.
• Hybrid work model with generous, flexible time off.
• In-office perks including free meals, snacks, and company-funded sport activities.
• AI-first work culture with default access to tools like Claude and OpenAI.