Senior Principal AI Architect/Engineer
Core
Design, deploy, and operate an enterprise-grade AI observability platform covering LLM workflows, multi-agent orchestration, and physical AI systems.
Role type
Senior Principal AI Architect/Engineer (Observability)
Builds
Unified telemetry pipelines, dashboards, alerting, and governance tools for agentic AI ecosystems.
Domain
Artificial Intelligence / Observability / Agentic Systems
Deliverable
production ML models | infrastructure | dashboards & analysis
Required skills
OpenTelemetry (OTEL), Python, Kafka, distributed tracing, multi-agent orchestration, reinforcement learning, data science, CI/CD automation, cloud infrastructure (Azure/AWS/GCP)
Preferred skills
Red teaming, Responsible AI (RAI) frameworks, MCP (Model Context Protocol), FinOps, statistical process control
Technologies
OpenTelemetry, Kafka, Python, Azure, AWS, GCP, Salesforce AgentForce, ServiceNow, Microsoft Agent 365
Responsibilities
Define enterprise observability architecture for AI agents and LLMs; build telemetry pipelines with metrics, logs, and traces; lead red team exercises and safety signal capture; integrate RAI metrics into observability pipelines; own Continuous Quality Engineering (CQE) frameworks; design observability for agent memory and reinforcement learning harnesses; lead a team of Python engineers building observability tooling.
Seniority
Principal, hands-on IC with team leadership