Senior AI Platform SRE – Reliability & FinOps Leader
Posted Updated
Description
Manychat is seeking an AI-native SRE to own reliability, performance, and cost of our AI infrastructure, including AI Gateway and inference services, across Bedrock, Azure OpenAI, and other providers.
You'll shape the AI Platform from the ground up, setting standards and roadmaps while ensuring the features critical to customer-facing automation meet SLAs and cost targets. This role offers high autonomy and direct partnership with the Head of Infrastructure.
Own reliability and performance of our AI infrastructure: AI Gateway, inference services, and integrations with Amazon Bedrock, Azure OpenAI, and other LLM providers. Design and evolve the AI Gateway: routing, failover between providers, rate limiting, caching, and guardrails. Build observability for AI systems: latency/throughput/error SLOs per model and provider, token-level metrics, quality and drift signals. Drive cost optimization and FinOps for AI workloads: per-feature cost visibility, model right-sizing, caching strategies, provider mix. Run capacity planning and incident response for inference services; write and improve runbooks and postmortems. Scale AI expertise across the org: set standards, review designs, and coach teams shipping LLM-backed features. 5+ years in SRE / platform / infrastructure engineering, including production ownership at significant scale. Hands-on experience operating LLM-backed systems in production with provider APIs (Bedrock, OpenAI, Anthropic, or similar). Deep cloud-native background: AWS, Kubernetes, Terraform/IaC, CI/CD. Strong observability practice (Prometheus/Grafana, OpenTelemetry, or equivalent) and experience defining SLOs. Hybrid onboarding Relocation support Health insurance Professional development budget Flexible benefits package Hybrid workSkills
Sign in to read and join the discussion.