Lead SRE - AI
- Location
- Abingdon, England, United Kingdom
anomaly detection, runbook automation, incident triage, and RCA summarization. Implement RAG (Retrieval‐Augmented Generation) pipelines over operational knowledge bases and runbooks. Integrate AI/ML models into SRE observability tools like New Relic and automation workflows, including monitoring, alerting, and self‐healing. Build and maintain RESTful and async APIs using … driven infrastructure automation using Terraform, Ansible, and Jenkins. Enforce engineering best practices, including code reviews, unit testing, and CI/CD pipelines for both ML and application code. Evaluate and introduce emerging AI frameworks and LLM providers, including OpenAI, Azure OpenAI, Bedrock, LangChain, and LlamaIndex. Maintain Kubernetes‐deployed AI workloads ...