Senior AI Engineer Agentic AI Platform

Job Details

• Job Title: Senior AI Engineer – Agentic AI Platform
• Location: Chicago, IL
• Onsite: Tuesday–Thursday, 3 days per week
• Remote: Monday and Friday
• Duration: 6 months
• Experience Required: 8–10 years
• Primary Skill: AI Agents

Position Summary

• Design and build an enterprise-scale Agentic AI platform.
• Enable multiple business domains to:
  • Develop AI agents
  • Deploy AI agents
  • Monitor AI agents
  • Govern AI agents
• Focus on enterprise AI platform engineering rather than basic LLM application development.
• Build production-grade AI systems with emphasis on:
  • Agent orchestration
  • AI platform architecture
  • Model governance
  • Memory management
  • Observability
  • Cost attribution
  • Multi-agent systems
  • Cloud-native architecture
  • Security and scalability

Agentic AI Solution Development

• Design and develop sophisticated multi-agent AI systems.
• Build autonomous and semi-autonomous AI workflows.
• Implement agent architectures including:
  • Supervisor-worker
  • Sequential
  • Orchestration
  • Choreography
  • ReAct
  • Planner-Executor
  • Writer-Critic
• Develop scalable agent communication and execution frameworks.
• Design closed-loop AI workflows with:
  • Validation
  • Retry mechanisms
  • Evaluation
  • Feedback loops

Enterprise AI Platform Engineering

• Build reusable AI platform capabilities for multiple business teams.
• Implement enterprise AI governance and operational controls.
• Design API-driven AI services with:
  • Rate limiting
  • Quota management
  • Multi-tenant usage tracking
  • Cost attribution
  • Authentication and authorization
  • Audit logging
• Establish structured onboarding and lifecycle management for AI agents.

Multi-Agent Orchestration

• Design agent communication through:
  • Direct API calls
  • Event-driven architectures
  • Message queues
  • Publish-subscribe patterns
• Implement:
  • Choreography-based execution
  • Conductor/orchestrator-based execution
• Evaluate and utilize technologies such as:
  • Kafka
  • Azure Durable Functions
  • Azure Service Bus
  • Event-driven workflows

AI Memory & Knowledge Systems

• Design short-term and long-term AI memory architectures.
• Implement:
  • Vector databases
  • Semantic caching
  • Conversation memory
  • Agent state persistence
  • RAG
• Develop knowledge orchestration frameworks supporting agent collaboration.

Ontology & Graph-Based Intelligence

• Work with graph databases and enterprise knowledge models.
• Support ontology-driven AI applications.
• Build knowledge graphs for:
  • Relationship-based reasoning
  • Signal generation
  • Knowledge discovery
• Combine:
  • Structured data
  • Unstructured data
  • Graph-based knowledge

Model Governance & FinOps

• Implement AI consumption governance across business domains.
• Track:
  • Token usage
  • Model consumption
  • API utilization
  • Operational costs
• Develop chargeback/showback mechanisms.
• Support AI FinOps reporting and capacity planning.
• Implement cost optimization strategies for enterprise AI workloads.

Reliability, Monitoring & Observability

• Design observability frameworks for AI applications.
• Monitor:
  • Agent executions
  • Tool usage
  • Latency
  • Hallucinations
  • Failure rates
  • Model quality
• Build dashboards and operational metrics for AI workloads.
• Implement comprehensive AI monitoring and logging.

Responsible AI & Security

• Implement:
  • AI guardrails
  • Safety controls
  • Prompt protection
  • Data masking
  • PII protection
  • Human-in-the-loop validation
• Ensure compliance with enterprise security and governance policies.
• Design secure agentic systems capable of handling sensitive business data.

AI Evaluation & Optimization

• Develop frameworks for:
  • Agent evaluation
  • Tool evaluation
  • Response quality measurement
  • Closed-loop evaluation
  • Hallucination detection
• Apply advanced AI engineering techniques:
  • Context engineering
  • Prompt engineering
  • Retrieval optimization
  • Agent tuning
  • AI benchmarking

Required Qualifications

• 7+ years of software engineering or platform engineering experience.
• 3+ years building AI/ML or Generative AI solutions.
• Experience delivering enterprise-scale production AI applications.
• Experience designing AI architectures, not just individual AI applications.
• Strong architecture and technology trade-off decision-making skills.

Generative AI & Agentic Frameworks

• Azure AI Foundry
• Azure OpenAI
• LangChain
• LangGraph
• Semantic Kernel — preferred
• MCP / Model Context Protocol
• Generative AI
• Agentic AI
• Multi-Agent Systems
• RAG

Cloud Platforms

• Microsoft Azure — Required
• GCP — Plus
• AWS — Plus

Enterprise Integration

• API gateways
• AI governance platforms
• Azure API Management (APIM)
• REST APIs
• Event-driven systems
• Multi-tenant AI architectures

Programming

• Python — Required
• C# / .NET — Preferred
• SQL

Data & Storage

• Cosmos DB
• PostgreSQL
• MongoDB
• Vector databases
• Graph databases
• Neo4j
• Stardog
• Amazon Neptune

Messaging & Streaming

• Kafka
• Azure Service Bus
• Azure Event Grid
• Azure Durable Functions
• Message queues
• Event-driven architecture

AI Operations

• AI observability
• Monitoring and logging
• Token usage analysis
• Cost optimization
• Model lifecycle management
• AI FinOps
• Model governance
• Production AI operations

Preferred Qualifications

• Experience implementing ontology-driven solutions.
• Enterprise knowledge graph experience.
• Experience building autonomous AI systems.
• Experience with AI governance and responsible AI frameworks.
• Experience designing reusable AI platforms consumed by multiple business units.
• Experience in regulated industries such as:
  • Healthcare
  • Financial Services
  • Insurance

Key Architecture Areas

• Architecture trade-offs
• Agent orchestration patterns
• Choreography vs. orchestration
• Multi-agent systems
• Memory management
• Graph databases
• Ontology
• Knowledge graphs
• AI platform governance
• APIM and AI gateway patterns
• Closed-loop evaluation
• Context engineering
• Harm and risk management
• Cost attribution
• Multi-tenant AI platforms

What Success Looks Like

• Deliver scalable multi-agent AI solutions for enterprise use cases.
• Establish reusable AI platform capabilities across multiple business domains.
• Implement AI governance, monitoring, and cost attribution frameworks.
• Build enterprise-grade orchestration patterns and memory architectures.
• Improve AI reliability, observability, and operational maturity.
• Enable business teams to rapidly develop AI-powered applications on a secure and governed platform.

Essential Skills

• Senior AI Engineer
• Agentic AI
• AI Agents
• Multi-Agent Systems
• Generative AI
• Azure AI Foundry
• Azure OpenAI
• LangChain
• LangGraph
• Python
• RAG
• Vector Databases
• AI Platform Engineering
• AI Architecture
• AI Governance
• AI Observability
• Azure
• Azure APIM
• API Gateways
• Distributed Systems
• Event-Driven Architecture
• AI FinOps
• Model Governance

Suggested Resume Search Keywords

• Senior AI Engineer
• Senior AI Platform Engineer
• Agentic AI Engineer
• Agentic AI Solutions Architect
• AI Platform Engineer
• Generative AI Engineer
• AI Solutions Architect
• AI Agents
• Agent Orchestration
• Multi-Agent Systems
• LangChain
• LangGraph
• Azure AI Foundry
• Azure OpenAI
• Python
• RAG
• Vector Database
• Knowledge Graph
• Ontology
• Azure APIM
• AI Governance
• Responsible AI
• AI Observability
• AI FinOps
• Model Governance