AI Platform SRE Lead: Reliability & Scale for LLM Infra

Manychat; Barcelona; Hybrid; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Relocation support

Health insurance for you and family

Professional development budget

Flexible benefits

Hybrid work model

In-office meals & snacks

Job summary

Manychat, a leading chat marketing platform, is seeking an AI Platform SRE to own the reliability, performance, and cost of our AI infrastructure and to raise the bar for how our engineering org builds on LLMs.

You will shape the AI Gateway, design routing and failover, run capacity planning and incident response, and build strong observability with Prometheus, Grafana, and OpenTelemetry, partnering directly with the Head of Infrastructure.

Qualifications

• 5+ years in SRE / platform / infra with production ownership.
• Hands-on experience operating LLM-backed systems in production.
• Cloud-native background: AWS, Kubernetes, Terraform/IaC, CI/CD.
• Strong observability practice and ability to define SLOs for non-deterministic systems.
• Proven cost-optimization work and making spend visible.
• Staff-level influence: set technical direction beyond your own team.

Responsibilities

• Own reliability and performance of our AI infrastructure: AI Gateway, inference services, and integrations with Bedrock, OpenAI, Anthropic, or similar.
• Design and evolve the AI Gateway: routing, failover, rate limiting, caching, and guardrails.
• Build observability for AI systems: latency/throughput/SLOs, token metrics, and drift signals.
• Drive cost optimization and FinOps for AI workloads: visibility, right-sizing, caching strategies.
• Run capacity planning and incident response for inference services; write/runbooks and postmortems.
• Scale AI expertise across the org: set standards, review designs, and coach teams shipping LLM-backed features.

Skills

SRE / infra

LLM production

Cloud-native

Observability

Cost optimization

Technical leadership

Tools

Prometheus

Grafana

OpenTelemetry

Job description

Manychat, a leading chat marketing platform, is seeking an AI Platform SRE to own the reliability, performance, and cost of our AI infrastructure and to raise the bar for how our engineering org builds on LLMs.

You will shape the AI Gateway, design routing and failover, run capacity planning and incident response, and build strong observability with Prometheus, Grafana, and OpenTelemetry, partnering directly with the Head of Infrastructure.