AI Platform/Observability Architect

ORION BUSINESS, LLC
Chicago, United States of America
yesterday

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English
Experience level
Senior

Job location

Chicago, United States of America

Tech stack

Artificial Intelligence
Amazon Web Services (AWS)
Azure
Cloud Computing
Continuous Integration
Information Engineering
DevOps
Distributed Systems
Monitoring of Systems
Python
Reliability Engineering
Prometheus
Software Safety
Software Engineering
Datadog
Google Cloud Platform
Grafana
AI Platforms
Git Flow
Kubernetes
Kafka
Machine Learning Operations
Virtual Agents
Splunk
Docker
Microservices

Job description

  • Architect and implement OTEL-based observability solutions for AI platforms.
  • Build telemetry pipelines, dashboards, alerts, and monitoring frameworks.
  • Define observability standards for Agentic AI, LLMOps, and AI platform services.
  • Implement AI safety, governance, quality, and compliance monitoring.
  • Develop Python-based observability tools, SDKs, and automation frameworks.
  • Collaborate with AI Engineering, SRE, Security, and Product teams to deliver scalable AI solutions.

Requirements

We are seeking an experienced AI Platform / Observability Architect with 10+ years of experience in Platform Engineering, Observability, Distributed Systems, and AI Platforms., * OpenTelemetry (OTEL)

  • AI Observability & Monitoring
  • Python Development
  • Distributed Systems & Microservices
  • Kubernetes, Docker, Kafka
  • Grafana, Datadog, Splunk, Prometheus
  • AWS, Azure, or Google Cloud Platform
  • CI/CD, DevOps, GitOps
  • Agentic AI (LangChain, LangGraph, AutoGen, Semantic Kernel, CrewAI)
  • AI Governance, Security & Responsible AI, * 10+ years of experience in Software Engineering, Platform Engineering, Data Engineering, or Observability.
  • Strong expertise in Python, OpenTelemetry, Cloud Platforms, and Distributed Systems.
  • Experience with AI/LLMOps platforms and Agentic AI frameworks is highly preferred.

Apply for this position