What are the responsibilities and job description for the Agentic AI Architect position at SID Global Solutions?
Agentic AI Architecture & Engineering
- Design and develop enterprise-scale Agentic AI and Generative AI platforms.
- Architect and implement AI Agents, Multi-Agent Systems, Autonomous Agents, AI Copilots, Intelligent Assistants, and Agentic Workflow Applications.
- Design and implement solutions using:
- LangChain
- LangGraph
- AutoGen
- CrewAI
- Agent Development Kit (ADK)
- Model Context Protocol (MCP)
- AI Agent Frameworks
- Agent Communication Protocols
- Agent Workflow Engines
- Design agent workflows, memory architectures, planning strategies, tool integrations, state management frameworks, and agent collaboration models.
- Build reusable AI agents, SDKs, frameworks, accelerators, reference architectures, and platform capabilities.
- Develop enterprise-scale Retrieval Augmented Generation (RAG) platforms leveraging semantic search, vector databases, embeddings, and enterprise knowledge systems.
- Design enterprise search platforms, AI knowledge bases, knowledge graphs, metadata frameworks, and content intelligence architectures.
- Build AI-powered decision support systems, intelligent workflow solutions, and business process automation capabilities.
- Design Human-in-the-Loop AI systems, approval workflows, escalation mechanisms, and responsible AI control frameworks.
- Lead development of intelligent automation solutions that transform business operations and enterprise workflows.
Full Stack AI-Powered Enterprise Application Development
- Design and develop end-to-end AI-powered enterprise applications from user experience through production deployment.
- Build enterprise software solutions including:
- AI Workbenches
- Enterprise Portals
- Customer-Facing Applications
- SaaS Platforms
- Workflow Automation Platforms
- Knowledge Management Systems
- Digital Experience Platforms
- Operational Dashboards
- AI-Powered Business Applications
- Architect complete application ecosystems spanning:
- Front-End Applications
- Backend Services
- APIs
- Agent Orchestration Layers
- Enterprise Integrations
- Security Frameworks
- Data Platforms
- Cloud Infrastructure
- Develop reusable user interface components, services, APIs, integration frameworks, and platform accelerators.
- Integrate AI capabilities into customer-facing applications, enterprise systems, and operational workflows.
- Implement scalable, resilient, secure, and maintainable enterprise application architectures.
- Lead application modernization initiatives that embed AI into existing enterprise systems and business processes.
Enterprise Architecture & Solution Design
- Define enterprise reference architectures, design standards, reusable patterns, and implementation frameworks.
- Architect end-to-end enterprise solutions spanning:
- AI Platforms
- Enterprise Applications
- Integration Layers
- Data Platforms
- Security Architectures
- Cloud Infrastructure
- Design AI-powered enterprise architecture patterns for intelligent automation and digital transformation.
- Develop enterprise integration strategies connecting AI solutions with internal and external business systems.
- Design application modernization strategies leveraging AI, automation, and cloud-native technologies.
- Establish architecture governance processes, technology standards, and engineering excellence practices.
AI Operations, Governance & Platform Engineering
- Establish AgentOps, MLOps, LLMOps, DevSecOps, AI Observability, and lifecycle management frameworks.
- Implement Responsible AI, AI Governance, AI Safety, AI Guardrails, and Enterprise Security controls.
- Define AI reliability, monitoring, tracing, benchmarking, evaluation, and operational excellence frameworks.
- Design and implement:
- AI Monitoring
- Prompt Monitoring
- Model Monitoring
- Distributed Tracing
- Observability Platforms
- Performance Analytics
- Develop automated testing frameworks for:
- AI Agents
- Multi-Agent Systems
- RAG Applications
- Prompt Engineering
- Retrieval Testing
- Regression Testing
- Guardrail Validation
- AI Evaluation
- Define quality metrics for:
- Accuracy
- Groundedness
- Retrieval Quality
- User Experience
- Reliability
- Latency
- Business Outcomes
- Operational Efficiency
- Optimize AI systems for scalability, reliability, maintainability, security, and cost effectiveness.