AI Solutions and Platforms Operations Engineer
Core
Builds and operationalizes agentic AI solutions using modern orchestration frameworks, contributing to an AI Agent Operations Center for safe, reliable, and observable agent behavior at scale.
Role type
Senior IC AI Solutions and Platforms Operations Engineer (Agentic Frameworks & AI Agent Operations Center Developer)
Builds
AI Agent Operations Center capabilities including agent registry, versioning, deployment tracking, run histories, incident triage, replay/debug workflows, and operational dashboards for agent health.
Domain
Artificial Intelligence / Generative AI / Observability / Cloud Infrastructure
Deliverable
production ML models | product features | dashboards & analysis
Required skills
Python, agentic frameworks (Crew.ai, LangChain, Semantic Kernel, AutoGen), RAG patterns (embeddings, vector search, retrieval evaluation), cloud environments (Azure/AWS/GCP), containerized deployments (Kubernetes/AKS/EKS), observability fundamentals (logs/metrics/traces), CI/CD pipelines, internal developer platforms, OpenTelemetry, distributed tracing, prompt/version management, evaluation frameworks, Responsible AI practices, FinOps (token/GPU cost optimization).
Preferred skills
Experience building and observing AI/ML or GenAI applications, experience with Azure AI Search / vector databases.
Technologies
Crew.ai, LangChain, Semantic Kernel, AutoGen, Python, Azure, AWS, GCP, Kubernetes, AKS, EKS, OpenTelemetry, Azure AI Search, vector databases.
Responsibilities
Build agent registry, versioning, deployment tracking, and run histories; Enable operational workflows such as incident triage, replay/debug runs, trace correlation, and root-cause analysis; Implement operational dashboards for agent health metrics; Instrument agent flows end-to-end using OpenTelemetry; Partner with SRE/observability teams for production-grade monitoring; Build and maintain CI/CD pipelines for agent services; Automate onboarding for new agent use cases.
Seniority
Mid-Senior, hands-on IC