Artificial Intelligence Architect

EXL; Pittsburgh (Allegheny County); Hybrid; USD 150,000 - 230,000; Full time

Job summary

EXL is seeking an AI Architect to design and modernize enterprise-grade GenAI/RAG platforms on Azure. You will architect agentic AI solutions, evolve LLM orchestration layers, and deploy in containerized, production-scale environments.

Hybrid work mix includes 3 days onsite and 2 days remote in Pittsburgh. Ideal candidates bring 8+ years of experience and hands-on expertise with Semantic Kernel, Microsoft Agent Framework, Python/Django, Azure AI Services, and robust observability using

Qualifications

• Must have hands-on experience refactoring SK plugins, planners, function calling, and memory to Agent Framework agents/workflows.
• Proficient in Python/Django to rebuild orchestration layer while preserving API contracts and RBAC permissions.
• Deep knowledge of Azure AI Services, RAG, Azure OpenAI, embeddings, and retrieval with proper citation paths.
• Familiarity with tool integration via MCP for the Intelligence Layer channel.
• Experience with OpenShift/containerized deployments and OCP.
• Experience with observability/validation using OpenTelemetry and Arize Phoenix.
• Strong GitHub CI/CD workflows and DevSecOps practices at scale.

Skills

Semantic Kernel

Microsoft Agent Framework

Python

Django

Azure AI Services

RAG

Model Context Protocol

GitHub CI/CD

DevSecOps

OpenTelemetry

Arize Phoenix

Tools

OpenShift

Containerization

Azure APIM

Redis Enterprise

Job description

Location: Pittsburgh, PA(Hybrid - 3 days onsite and 2 days' work from home)

Experience: 8+ years

About the Role

We are looking for an AI Architect with deep hands-on expertise in building and modernizing enterprise-grade GenAI/RAG platforms on the Microsoft Azure ecosystem. The role involves architecting agentic AI solutions and evolving LLM orchestration layers on modern agent frameworks, working with containerized, production-scale environments.

Must-Have Skills

• Semantic Kernel + Microsoft Agent Framework - hands-on experience refactoring SK plugins, planners, function calling, and memory to Agent Framework agents/workflows (this is the critical, hardest-to-source skill)
• Python / Django - to rebuild the orchestration layer without breaking existing API contracts, RBAC, and permissions
• Azure AI Services / RAG - Azure AI Search (hybrid retrieval, semantic ranking), Azure OpenAI (inference + embeddings), preserving retrieval, reranking, prompt assembly, and citation paths.

High-Priority Skills

• Model Context Protocol (MCP) - for tool/connector integration and the Intelligence Layer channel
• OpenShift / containerization - to deploy migrated microservices on OCP
• Observability & Evaluation - Arize Phoenix + OpenTelemetry instrumentation, agent/agentic-system registration, and RAG quality/eval validation to confirm parity
• GitHub / CI-CD / DevSecOps - PR-based workflows and vulnerability remediation

Medium-Priority Skills

• Redis Enterprise (caching/session state) and Azure APIM (gateway, rate limiting).