GenAI Architect

Key Responsibilities

• Define enterprise-wide Generative AI architecture strategy, standards, and best practices.
• Design scalable and secure LLM-powered solutions using Azure OpenAI and Azure AI Services.
• Architect enterprise-grade RAG platforms leveraging vector databases, semantic search, and knowledge management systems.
• Design and govern Agentic AI ecosystems utilizing AI Agents, tool calling, orchestration, and autonomous workflows.
• Evaluate and select appropriate foundation models, embeddings, and multimodal architectures based on business requirements.
• Design AI platforms supporting:
• Enterprise Chatbots
• Intelligent Search
• Knowledge Assistants
• Document Intelligence
• Software Engineering Assistants
• Business Process Automation
• Define reference architectures for:
• Multi-agent systems
• RAG pipelines
• AI gateways
• Model serving
• Prompt management
• Evaluation frameworks
• Establish AI governance, Responsible AI, security, privacy, compliance, and risk management controls.
• Architect solutions utilizing Vision LLMs, OCR, and multimodal AI capabilities.
• Guide engineering teams on implementation patterns using LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, and other AI frameworks.
• Define observability, monitoring, evaluation, and feedback-loop mechanisms for AI applications.
• Lead technical design reviews, architecture governance boards, and AI solution assessments.
• Optimize AI solutions for scalability, reliability, latency, cost, and performance.
• Define CI/CD and MLOps strategies for AI solution deployment.
• Collaborate with enterprise architects, cloud architects, security teams, and business stakeholders to align AI initiatives with organizational goals.
• Mentor AI engineers, data scientists, and development teams on modern GenAI architectures and engineering practices.
• Stay current with emerging AI technologies, models, frameworks, and industry trends.

Required Skills

Generative AI & LLMs

• Large Language Models (LLMs)
• GPT-4o, GPT-4.1, Claude, Gemini, Llama
• Prompt Engineering
• Retrieval-Augmented Generation (RAG)
• Embeddings
• Semantic Search
• AI Agents
• Function Calling
• Context Engineering
• Memory Management
• Model Evaluation
• Fine-Tuning Concepts
• Multi-Agent Systems
• Agent Orchestration

Agentic AI Frameworks

• LangGraph
• LangChain
• LlamaIndex
• CrewAI
• AutoGen
• Semantic Kernel
• OpenAI SDK
• MCP (Model Context Protocol)

Cloud & AI Platforms

• Azure OpenAI Service
• Azure AI Foundry
• Azure AI Search
• Azure AI Services
• Azure Document Intelligence
• Azure Functions
• Azure Kubernetes Service (AKS)
• Azure API Management
• Azure Storage
• Azure Key Vault
• Azure Monitor

Architecture & Enterprise Design

• Enterprise Architecture Frameworks
• Solution Architecture
• Cloud-Native Architecture
• Event-Driven Architecture
• API-Led Architecture
• Microservices Design
• High Availability Design
• Scalability Engineering
• Security Architecture
• Integration Architecture

Data & Vector Technologies

• Azure AI Search
• FAISS
• Pinecone
• Weaviate
• ChromaDB
• PostgreSQL
• Cosmos DB
• Redis
• Knowledge Graphs
• Data Modeling

Programming & Development

• Python (Expert)
• FastAPI
• REST APIs
• Asynchronous Programming
• Docker
• Kubernetes
• GitHub
• Azure DevOps
• CI/CD Pipelines

Observability & Evaluation

• Opik
• LangSmith
• MLflow
• Prompt Evaluation
• LLM Monitoring
• Experiment Tracking
• AI Quality Metrics
• Hallucination Detection
• Performance Benchmarking

Security & Governance

• Responsible AI
• AI Governance Frameworks
• Data Privacy
• Model Security
• Prompt Injection Protection
• AI Risk Management
• Compliance Controls
• Enterprise Security Standards

Required Experience

• 10+ years of overall software engineering and architecture experience.
• 5+ years of solution architecture experience in cloud-native environments.
• 3+ years of hands-on experience in Generative AI and LLM solution architecture.
• Proven experience designing enterprise-scale RAG platforms.
• Experience architecting AI Agent and multi-agent solutions.
• Strong expertise with Azure OpenAI and Azure AI ecosystem.
• Experience defining AI governance, security, and Responsible AI frameworks.
• Hands-on experience with vector databases and semantic search solutions.
• Experience designing multimodal AI applications involving text, image, and document intelligence.
• Experience leading technical teams and driving architecture decisions across large organizations.
• Experience implementing MLOps and AI platform engineering practices.
• Strong stakeholder management and client-facing consulting experience.

Preferred Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or related field.
• Microsoft Certified:
• Azure Solutions Architect Expert
• Azure AI Engineer Associate
• Azure AI Fundamentals
• Experience working with Fortune 500 enterprise AI transformation programs.
• Experience with GenAI governance and AI Center of Excellence (CoE) initiatives.
• Knowledge of FinTech, Healthcare, Insurance, Retail, or Banking domain AI implementations.

Nice-to-Have Skills

• NVIDIA NIM
• Hugging Face Ecosystem
• GraphRAG
• Neo4j
• Databricks
• Snowflake Cortex
• Vertex AI
• Amazon Bedrock
• OpenTelemetry
• AI Gateway Platforms
• Federated AI Architectures
• Knowledge Graph Solutions
• Vector Database Benchmarking
• Enterprise CoPilot Development
• AI Platform Engineering

Experience Range

12-18+ Years

Target Profile

This role is suitable for a GenAI Solution Architect / AI Architect / Enterprise AI Architect who can define enterprise AI strategy, architect scalable GenAI platforms, govern AI adoption, and lead large-scale AI transformation initiatives beyond hands-on development.