Senior AI Observability engineer
Core
Build an AI-native operations layer using LLM agents and ML anomaly detection to find, triage, and remediate incidents across hybrid cloud and on-premises infrastructure.
Role type
Senior hands-on IC AIOps Reliability Engineer
Builds
AI-native incident response systems, agentic workflows, and telemetry-driven observability layers
Domain
Cloud infrastructure, SRE, and Generative AI
Deliverable
production ML models
Required skills
LLM agent orchestration, time-series anomaly detection, vector database engineering, cloud-agnostic infrastructure design, AI safety and governance, LLMOps/MLOps, OpenTelemetry GenAI tracing
Preferred skills
Experience with Azure, AWS, and Google Cloud; on-premises data center operations; manufacturing and HPC facility infrastructure
Technologies
LangGraph, Semantic Kernel, AutoGen, Model Context Protocol, vector stores, OpenTelemetry GenAI, ServiceNow, CMDB
Responsibilities
Build agentic AI workflows for autonomous fault detection and remediation; develop the AIOps intelligence layer for anomaly detection and alert correlation; engineer retrieval knowledge fabrics from runbooks and architecture docs; ship AI-assisted incident response and automated remediation pipelines; own AI safety, guardrails, and evaluation harnesses; run LLMOps and MLOps including model versioning and cost/latency observability; instrument AI systems with SLOs and quality dashboards
Seniority
Senior, hands-on IC
