Engineer III - AI Powered SRE (UK Shift Timing)
Core
Build AI agents and intelligent automation systems to autonomously detect, diagnose, and remediate operational issues across large-scale distributed infrastructure, reducing human toil.
Role type
Senior IC SRE specializing in AI agent development and intelligent automation
Builds
Autonomous operations tooling, AI-driven automation pipelines, and self-healing infrastructure components
Domain
Cybersecurity, Distributed Systems, AI/ML Operations
Deliverable
production ML models
Required skills
Python, Go, Java, C++, LLM integration, Prompt engineering, RAG, Agentic frameworks (LangChain, AutoGen, CrewAI), Linux administration, Kubernetes, Monitoring stacks (ELK, Prometheus, Grafana), Configuration management (Puppet, Chef, Ansible)
Preferred skills
MLOps, AI observability, Self-healing infrastructure experience, Open-source AI contributions
Technologies
LangChain, AutoGen, CrewAI, LlamaIndex, ELK, Prometheus, Grafana, Kubernetes, Docker, VMware, Ansible, Puppet, Chef, LangSmith, Weights & Biases, Arize
Responsibilities
Design and develop AI agents for autonomous incident response; Build event-driven automation pipelines using LLMs; Integrate agentic workflows with monitoring and telemetry stacks; Instrument and evaluate agent performance; Collaborate on incident analysis and post-incident reviews; Write technical documentation for automation systems and runbooks
Seniority
Senior, hands-on IC
