SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
ManyChat is hiring a Staff Site Reliability Engineer to own the reliability, performance, and cost of its AI infrastructure platform. This is a greenfield opportunity to shape architecture from the ground up, not maintain legacy systems.
You will own end-to-end reliability of the AI Gateway, inference services, and integrations with Amazon Bedrock, Azure OpenAI, and other LLM providers. Key responsibilities include:
• 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 optimization
• 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
This role requires 5+ years in SRE, platform, or infrastructure engineering with production ownership at significant scale. You must have hands-on experience operating LLM-backed systems in production (provider APIs, inference pipelines, model serving). Deep cloud-native expertise (AWS, Kubernetes, Terraform, CI/CD) and strong observability practice (Prometheus/Grafana, OpenTelemetry) are essential. You should have proven cost-optimization work and staff-level influence setting technical direction beyond your own team.
Desirable experience includes building/operating LLM gateways (LiteLLM, Kong AI Gateway), GPU workload optimization, quantization, serving frameworks (vLLM, TGI, Triton), and eval pipelines for LLM quality monitoring.
ManyChat is a 400+ person company across three continents building an AI-powered platform for conversational growth across Instagram, Messenger, WhatsApp, and TikTok. The AI Platform is young and critical to the business—your work directly impacts customer-facing automation at scale. You'll partner directly with the Head of Infrastructure with real autonomy and visibility.
The company offers hybrid work with flexible time off, comprehensive health insurance, professional development budget, flexible benefits package, in-office perks, and company-funded activities.
