Agent可观测研发工程师
Core
Designing and optimizing high-concurrency distributed systems for Tencent Cloud's Cloud Log Service (CLS) platform, specifically focusing on observability capabilities for AI Agents.
Role type
Senior IC backend engineer (distributed systems & observability)
Builds
Cloud Log Service platform, AI Agent observability SDKs, data ingestion pipelines supporting OTLP/Kafka protocols
Domain
Cloud infrastructure, distributed systems, AI observability
Deliverable
production ML models | product features
Required skills
Golang/Python/C/C++/Rust, Linux, TCP/IP/HTTP/gRPC, data structures and algorithms, distributed system architecture
Preferred skills
Log service/observability platform development, AI Agent observability (OpenTelemetry probes, GenAI semantic conventions), OpenTelemetry/Prometheus ecosystem, AI Coding tools (Cursor, Claude Code)
Responsibilities
Design and optimize large-scale high-concurrency distributed system architecture; Develop AI Agent observability capabilities including Logs/Traces/Metrics data collection and SDKs; Implement data ingestion and delivery capabilities supporting OTLP and Kafka protocols; Contribute to GenAI semantic standardization; Solve complex technical challenges and mentor team members