腾讯云-MaaS可用性高级研发工程师(北/杭/深)
Core
Build and maintain the stability infrastructure for Tencent Cloud's MaaS (Model-as-a-Service) platform, ensuring high availability for model inference and serving.
Role type
Senior SRE / Platform Engineering Engineer (MaaS Stability)
Builds
Unified observability platform, alerting systems, change management tools, and automated fault handling capabilities for the MaaS platform.
Domain
Cloud Infrastructure / Large Language Model (LLM) Serving / High Availability Systems
Deliverable
production ML models
Required skills
Golang, Java, Python, C++, Distributed Systems Architecture, Observability (Metrics/Logs/Traces), Alerting Systems, Change Management & Rollback, Fault Isolation & Circuit Breaking, Capacity Planning, Performance Analysis
Preferred skills
Cloud Platform Development, SRE/DevOps Platform Experience, MaaS/LLM Inference Experience
Responsibilities
Design and implement fault prevention, detection, mitigation, and recovery capabilities; Build multi-dimensional monitoring for tenants, models, and regions; Establish tiered alerting with noise reduction; Manage code, config, and model version changes with gray release and rollback; Collaborate on rate limiting, circuit breaking, and failover strategies; Lead load testing, capacity assessment, and chaos engineering.
Seniority
Senior, hands-on IC
