Agentic AI Platform / Solution Architect

<>Agentic AI Solution Development

• Design and develop sophisticated multi-agent AI systems for enterprise use cases.
• Build autonomous and semi-autonomous AI workflows using Agentic AI patterns.
• Implement supervisor-worker, sequential, orchestration, choreography, ReAct, Planner-Executor, and Writer-Critic architectures.
• Develop scalable agent communication and execution frameworks.
• Design closed-loop AI workflows with validation, retry, evaluation, and feedback mechanisms.

<>Enterprise AI Platform Engineering

• Build reusable AI platform capabilities consumed by multiple business teams.
• Implement enterprise-grade AI governance and operational controls.
• Design API-driven AI service architectures supporting:
• Rate limiting
• Quota management
• Multi-tenant usage tracking
• Cost attribution
• Authentication & authorization
• Audit logging
• Enable structured onboarding and lifecycle management of AI agents.

<>Multi-Agent Orchestration

• Design agent communication using direct calls, event-driven architectures, message queues, and publish-subscribe patterns.
• Implement choreography and conductor-based execution models.
• Evaluate and integrate technologies such as Kafka, Azure Durable Functions, Azure Service Bus, and 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, and 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 enabling relationship-based reasoning and signal generation.
• Combine structured, unstructured, and graph-based knowledge sources.

<>Model Governance & FinOps

• Implement AI consumption governance across business domains.
• Track token usage, model consumption, API utilization, and operational costs.
• Create chargeback/showback mechanisms for enterprise teams.
• Support AI FinOps reporting and capacity planning.

<>Reliability, Monitoring & Observability

• Design observability frameworks for AI applications.
• Monitor agent executions, tool usage, latency, hallucinations, failure rates, and model quality.
• Create dashboards and operational metrics for enterprise AI workloads.

<>Responsible AI & Security

• Implement guardrails, safety controls, prompt protection, data masking, PII protection, and human-in-the-loop validation.
• Ensure compliance with enterprise security and governance policies.
• Build secure agentic systems handling sensitive business data.

<>AI Evaluation & Optimization

• Develop frameworks for agent evaluation, tool evaluation, response quality measurement, closed-loop evaluation, and hallucination detection.
• Apply advanced AI engineering techniques including:
• Context engineering
• Prompt engineering
• Retrieval optimization
• Agent tuning
• AI system benchmarking

We are seeking a highly skilled Senior AI Engineer to help design and build an enterprise-scale Agentic AI platform that enables multiple business domains to develop, deploy, monitor, and govern autonomous AI agents.

This is an architecture-focused AI engineering role requiring hands-on expertise in agent orchestration, AI platform architecture, model governance, memory management, observability, cost attribution, multi-agent systems, and scalable cloud-native AI solutions.

The ideal candidate will have experience building production-grade AI systems using Azure AI Foundry, Azure OpenAI, LangChain, LangGraph, vector databases, API gateways, and modern AI engineering practices., * 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 and platforms, not just individual AI applications.
• Strong hands-on experience with AI Agents / Agentic AI.
• Python - required.
• Microsoft Azure - required.
• Experience with:
• Azure AI Foundry
• Azure OpenAI
• LangChain
• LangGraph
• MCP (Model Context Protocol)
• Strong understanding of multi-agent orchestration patterns.
• Experience with AI platform governance, observability, and cost management.
• Experience with Azure API Management (APIM) and REST APIs.
• Strong understanding of event-driven systems.
• Experience with vector databases and RAG architectures.
• Strong understanding of AI memory and knowledge management.
• Experience with AI monitoring, logging, token usage analysis, and cost optimization.

Technical Skills

Programming: Python, SQL; C#/.NET preferred

Cloud: Microsoft Azure required; Google Cloud Platform/AWS is a plus

AI/ML & Agentic AI: Azure AI Foundry, Azure OpenAI, LangChain, LangGraph, Semantic Kernel, MCP

Enterprise Integration: Azure APIM, REST APIs, AI gateways, event-driven architectures

Data & Storage: Cosmos DB, PostgreSQL, MongoDB, Vector Databases, Graph Databases

Graph Technologies: Neo4j, Stardog, Neptune, or similar

Messaging & Streaming: Kafka, Azure Service Bus, Event Grid, Durable Functions

AI Operations: AI observability, monitoring/logging, token usage analysis, cost optimization, model lifecycle management

Preferred / Desirable Skills

• Experience implementing ontology-driven AI solutions.
• Experience with enterprise knowledge graphs.
• 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 healthcare, financial services, insurance, or other regulated industries.
• Strong architecture and technical leadership capabilities.

Architecture Focus - Important

This is not a traditional LLM application-development role. Candidates should be able to discuss and demonstrate practical experience with:

• Architecture trade-offs
• Agent orchestration patterns
• Choreography vs. orchestration
• AI memory management strategies
• Graph databases and ontology
• AI platform governance
• APIM and AI gateway patterns
• Closed-loop AI evaluation
• Harm/risk/context engineering
• Cost attribution
• Multi-tenant AI platforms
• Enterprise Agentic AI architecture

The ideal candidate should be capable of making architecture decisions, evaluating technology trade-offs, and designing secure, scalable, observable, and governed enterprise AI platforms.

Preferred title alignment: Senior AI Platform Engineer - Agentic AI / Agentic AI Solutions Architect