Senior Site Reliability Engineer — Token Factory (Inference Platform)
Core
Own the reliability, performance, and observability of a massive GPU inference platform serving foundation models (text, vision, audio) at scale.
Role type
Senior Site Reliability Engineer (Inference Platform)
Builds
High-throughput inference stack for multimodal AI models
Domain
Cloud Infrastructure / AI Inference / GPU Orchestration
Deliverable
production ML models
Required skills
Kubernetes, Prometheus, Grafana, Terraform, Infrastructure-as-Code, Python, Bash, Alert Design, SLOs, Distributed Systems Debugging, GPU Workload Management
Preferred skills
vLLM, Triton, Ray, MLOps, Model Hosting Platforms, Kernel-level Debugging
Technologies
Kubernetes, Prometheus, Grafana, Terraform, vLLM, Triton, Ray
Responsibilities
Design and refine telemetry pipelines for metrics, logs, and traces; tune Kubernetes autoscalers for GPU efficiency; craft Terraform modules for cluster resilience; harden request-routing and retry logic; detect, isolate, and remediate incidents via automation; drive post-mortem culture.
Seniority
Senior, hands-on IC