Leave us your email address and we'll send you all the new jobs according to your preferences.

2026 - SRE Agent - Senior Agent Engineer - Contractor

Posted 54 minutes 43 seconds ago by Huawei Ireland Research Center

Permanent

Full Time

Academic Jobs

Dublin, Ireland

Job Description

Key Job Responsibilities

Agentic SRE Development: Design and implement core modules of highly reliable and scalable Agentic Site Reliability Engineering (SRE) systems, ensuring seamless integration between LLM reasoning and cloud infrastructure.
Extreme Risk Modeling: Execute comprehensive extreme risk analysis for hyper scale cloud services, applying Agentic AI to identify systemic vulnerabilities and control loop failures.
Autonomous Chaos Implementation: Develop and deploy autonomous chaos engineering workflows to proactively test and validate system resilience against non linear, cascading failures in production.
Reliability Logic Codification: Translate complex SRE domain knowledge into Agentic logic, specifically focusing on the implementation of tri tier memory systems (Semantic, Episodic, Procedural).

Basic Qualifications

Distributed Systems Implementation: 5+ years of hands on experience in the development and maintenance of large scale distributed systems within cloud environments.
Software Engineering: 5+ years of software development experience utilizing modern programming languages such as Golang, Java, Rust, or C++, with a focus on high concurrency and fault tolerant code.
System Theory Application: Strong understanding and applied experience with system theories and hazard analysis techniques, specifically STPA (Systems Theoretic Process Analysis) and FMEA (Failure Mode and Effects Analysis).
Reliability & Workload Modeling: Proficient in modeling cloud workload characteristics and system behaviors; ability to abstract raw telemetry (Metrics/Logs/Traces) into formal SRE metrics to detect intent shifts and implicit dependencies.

Preferred Qualifications

Agentic AI Engineering: Practical experience with Agentic AI frameworks (e.g., LangGraph, AutoGen, ADK), RAG architectures, and Agent-to-Agent (A2A/MCP) protocols. Knowledgeable in context engineering and LLM inference optimization.
Industry Recognition: Demonstrated, industry recognized achievements in the field of SRE, AI, or distributed systems, such as published academic papers, relevant patents, or speaking engagements at major technology conferences (such as EuroSys, SRECon).