Gen AI Architect

Key Responsibilities

GenAI & Agentic AI Architecture

• Architect end-to-end GenAI-first and Agentic AI solutions on AWS using:
• Amazon Bedrock
• Amazon AgentCore
• Strands SDK Multi-Agents
• AWS Agents for Bedrock
• Knowledge Bases for Bedrock
• Guardrails for Bedrock
• Amazon SageMaker for model lifecycle & finetuning
• Design multi-agent systems supporting planning, reasoning, tool invocation, memory stores, and multi-step workflows.
• Develop high-performance RAG architectures using:
• Amazon OpenSearch Serverless
• Kendra
• Aurora + pgvector
• Redis Enterprise
• Implement secure prompt flows, tool integrations, embeddings pipelines, and evaluation frameworks optimized for AWS.

Application & Platform Engineering

• Build Python-based microservices (FastAPI/Django) integrated with AWS AI stack.
• Design scalable architectures using AWS-native components:
• Lambda, Step Functions, EventBridge, SQS, DynamoDB, API Gateway, ECS/EKS
• Implement enterprise-class LLMOps using:
• Amazon SageMaker Pipelines
• AWS CodePipeline / CodeBuild
• CloudWatch / X-Ray observability
• Establish standards for:
• Agent governance & safety
• Secure model invocation
• Guardrails & content filters
• Latency & cost optimization patterns

Security, Reliability & Optimization

• Ensure compliance with enterprise security standards using:
• IAM, KMS, VPC endpoints, PrivateLink, CloudTrail
• Optimize AI workloads for cost, performance, and scalability, including model caching, selective batching, and autoscaling strategies.
• Conduct architecture reviews, threat modeling, and performance benchmarking.

Innovation & Framework Evangelism

• Assess new AWS AI services, foundation models, agent frameworks, and vector DBs.
• Create internal accelerators, reusable patterns, and AWS-focused reference architectures for:
• Multi-agent orchestration
• RAG 2.0 / context enrichment
• Federated retrieval
• Enterprise tool integration
• Lead PoCs, prototypes, and technical spikes to validate emerging AWS GenAI capabilities.

Technical Mentorship & Enablement

• Mentor engineering teams on AWS GenAI patterns, LLMOps, cloud-native development, and distributed AI architectures.
• Provide technical direction, best practices, and deep architectural guidance across delivery teams.
• Create internal documentation, architecture blueprints, and engineering playbooks.

Required Skills & Qualifications

• AWS Certified Associate/Professional Solutions Architect.

Preferred Qualifications

• Expert-level experience with AWS Bedrock, AWS AgentCore, Strands SDK, AWS Agents, SageMaker, OpenSearch, Lambda, Step Functions, ECS/EKS, and DynamoDB.
• Strong Python development background (FastAPI, Django).
• Hands-on coding ability with:
• Enterprise RAG
• Agent orchestration frameworks (Strands, LangGraph, CrewAI, Bedrock Agents, etc.)
• Embedding models and vector DB design
• Exposure to data engineering, analytics, and AI-driven platforms.
• Experience in pre-sales, solutioning, and deal shaping for large digital transformation programs.

Key Responsibilities

GenAI & Agentic AI Architecture

• Architect end-to-end GenAI-first and Agentic AI solutions on Azure using:
• Azure OpenAI Service
• Azure AI Foundry
• Azure Agents (Agent Service + Agent Runtime)
• Microsoft Agent Framework SDK
• Azure Machine Learning (Azure ML) for model lifecycle, fine-tuning & evaluation
• Design multi-agent systems capable of planning, reasoning, memory management, tool invocation, and complex workflow execution.
• Architect enterprise-grade RAG systems using:
• Azure Cognitive Search
• Azure AI Search Vector Stores
• Cosmos DB + pgvector
• Redis Enterprise on Azure
• Build secure prompt pipelines, embeddings workflows, tool integration layers, and model evaluation frameworks optimized for Azures GenAI stack.

Application & Platform Engineering

• Build Python-based microservices (FastAPI/Django) tightly integrated with Azure AI and cloud-native components.
• Implement enterprise-grade LLMOps using:
• Azure ML Pipelines
• Azure DevOps (ADO)
• GitHub Actions for MLOps/LLMOps
• Azure Monitor, App Insights, Log Analytics for observability
• Establish engineering standards for:
• Agent governance & safety
• Content filters & guardrails (Azure OpenAI Safety Systems)
• Secure model invocation via private endpoints
• Latency reduction, performance tuning & cost governance

Security, Reliability & Optimization

• Optimize AI workloads using model caching, selective batching, adaptive routing, vector index optimization, and autoscaling strategies on AKS/Functions.
• Lead architecture reviews, threat modeling, cost modeling, and performance benchmarking for large-scale GenAI workloads.

Innovation & Framework Evangelism

• Evaluate new Azure GenAI capabilities, FMs, agent frameworks, vector databases, and orchestration tools.
• Build internal accelerators and reusable reference architectures for:
• Multi-agent orchestration with Azure Agents Framework, Langgraph, CrewAI
• RAG 2.0 and context enrichment pipelines
• Federated & hybrid retrieval patterns
• Enterprise system/tool integration
• Drive PoCs, prototypes, and tech spikes to validate emerging Azure GenAI capabilities and accelerate enterprise adoption.

Technical Mentorship & Enablement

• Mentor engineering teams on Azure GenAI engineering, LLMOps, cloud-native patterns, and distributed AI architectures.
• Provide deep technical guidance, best practices, and architectural oversight across delivery projects.
• Develop internal documentation, architecture blueprints, engineering guides, and reusable templates.

Required Skills & Qualifications

• Microsoft Certified Azure Solutions Architect Expert or equivalent Azure Architect certification.
• Strong hands-on experience designing AI/ML or GenAI systems on Azure.

Preferred Qualifications

• Expert-level experience with:
• Azure OpenAI, Azure AI Foundry, Azure Agents Framework, Langgraph, CrewAI, Azure ML
• Cognitive Search, Cosmos DB, AKS, Functions, APIM, Event Grid, Service Bus
• Strong Python development background (FastAPI, Django).
• Hands-on coding experience in:
• RAG systems
• Agent orchestration frameworks (Azure Agents, LangGraph, CrewAI, etc.)
• Embedding models, vector indexing & vector DB architecture
• Exposure to data engineering, analytics, and cloud-scale distributed systems.
• Experience supporting pre-sales, architecture assessments, and solutioning for GenAI transformation programs.