Live opening · Posting date unavailable
AI Infra SRE 工程师(大模型推理)(深圳/北京)
Tencent · Shenzhen, China
At a glance
The key details from the original listing.
CompanyTencent
LocationShenzhen, China
Experience> 3 years of working experience
SkillsKubernetes
Source
Own
ListedPosting date unavailable
About the role
Description supplied by the original job listing.
1.负责大模型在线推理服务（含评测、潮汐调度等业务形态）的全链路稳定性保障：日常值班、告警响应、故障定位与复盘，推动根因治理与长期改善；
2.负责推理服务性能与容量运营：KV Cache 调优、吞吐与时延优化、GPU 资源池水位监控与弹性调度，参与成本 / 资源优化专项；
3.建设面向推理场景的可观测体系：TTFT / TPOT、缓存命中率、GPU 利用率、排队时延等 SLI/SLO 指标落地，结合 Tracing / Logging 定位长尾问题；
4.参与推理集群（Kubernetes）日常运维：多机多卡部署与调度策略、Pod 异常与故障节点隔离、灰度发布与回滚预案；
5.沉淀 SRE 工具链与效能建设：巡检工具、故障自愈脚本、容量与成本预测模型，持续降低人工运维成本。
Experience
> 3 years of working experience
More openings worth a look
Recently tracked roles with full details and direct application links.
Good roles move before most people even see them.
Tell JobBeeper what you want and get fresh matches delivered in minutes.
Create free account →