Senior Inference Platform SRE & Automation Engineer
Posted Updated
Description
Bitdeer Technologies Group seeks an experienced Site Reliability Engineer to own end-to-end reliability of a high-availability inference platform. You will manage API gateways, inference routers, schedulers, and KV caches, ensuring SLA-aligned performance across GPU-backed models and multi-cluster deployments.
The role emphasizes strong Kubernetes operations, Go/Python automation, and robust observability. Collaboration with cross-functional teams and a focus on automation and incident response
End-to-end availability of customer inference endpoints — API availability, request success rate, TTFT/TPOT latency, and the published SLA. The serving path: API gateway, inference router, health-based routing, request scheduling, queueing and admission control, prefill/decode serving, and the KV cache service. Inference runtime operations: engine health, model load and readiness validation, model revision rollout and rollback. Model replica topology and failure isolation across GPUs and NVLink/NCCL. Multi-cluster serving across MY/SG/JP with cross-cluster traffic steering and regional recovery. 5+ years in SRE / production platform operations, including 2+ years on a customer-facing API service operating against a published SLA. Deep Kubernetes operations experience with multi-cluster topologies. Hands-on production experience serving LLM/model inference APIs and complex workloads.Skills
Sign in to read and join the discussion.