Artificial Intelligence Architect

ID Softsource; Coimbatore; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

ID Softsource in Coimbatore, Tamil Nadu, seeks an experienced AI Architect with 4+ years in AI/GenAI, agentic AI, LLM applications, and production AI systems. The role translates business needs into scalable AI solutions and leads the development and deployment lifecycle.

You will design end-to-end AI architectures, supervise data flows, API integrations, and MCP-based tool ecosystems, while ensuring security, observability and governance across projects.

Qualifications

• 4+ years of experience in AI/GenAI architecture and production AI systems.
• Experience designing end-to-end AI and agent architectures.
• Ability to provide technical leadership across development and deployment lifecycle.

Responsibilities

• Design end-to-end AI/GenAI architecture, including system components, data flows, agent flows, API integrations, and deployment architecture.
• Translate business and functional requirements into scalable, secure, and production-ready AI solutions.
• Design and implement Agentic AI systems, including AI agents, planning, reasoning, task decomposition, routing, and orchestration.
• Design multi-agent architectures, including Supervisor Worker patterns, agent delegation, handoffs, coordination, and failure/recovery mechanisms.
• Evaluate and select appropriate LLMs/models based on use cases, performance, cost, latency, and reliability.
• Design and implement RAG architectures, vector search, embeddings, retrieval strategies, and knowledge-based AI solutions.
• Architect tool calling, function calling, API integrations, and enterprise service integrations for AI agents.

Skills

AI Architecture

GenAI Architecture

LLM Applications

Production AI

Technical Leadership

Tools

Docker

APIs

Cloud Platforms

MCP (Model Context Protocol)

Job description

We are looking for an experienced AI Architect with 4+ years of experience in AI/GenAI architecture, agentic AI, LLM applications, and production AI systems. The candidate will be responsible for translating business requirements into scalable AI solutions, designing end-to-end AI/agent architectures, and providing technical leadership throughout the development and deployment lifecycle.

Roles & Responsibilities

• Design end-to-end AI/GenAI architecture, including system components, data flows, agent flows, API integrations, and deployment architecture.
• Translate business and functional requirements into scalable, secure, and production-ready AI solutions.
• Design and implement Agentic AI systems, including AI agents, planning, reasoning, task decomposition, routing, and orchestration.
• Design multi-agent architectures, including Supervisor Worker patterns, agent delegation, handoffs, coordination, and failure/recovery mechanisms.
• Evaluate and select appropriate LLMs/models based on use cases, performance, cost, latency, and reliability.
• Design and implement RAG architectures, vector search, embeddings, retrieval strategies, and knowledge-based AI solutions.
• Architect tool calling, function calling, API integrations, and enterprise service integrations for AI agents.
• Design and integrate MCP (Model Context Protocol)-based tool ecosystems and connect AI agents with enterprise applications and services.
• Define AI workflow and state-management architectures, including agent memory, context management, and conversation state.
• Establish AI evaluation, guardrails, observability, monitoring, security, and reliability practices for production systems.
• Prepare and maintain HLD/LLD, architecture diagrams, technical specifications, and solution documentation.
• Define AI project technical roadmaps, milestones, delivery plans, and development priorities.
• Work closely with developers, project managers, business teams, and other technical stakeholders to ensure successful project delivery.
• Provide technical leadership and guidance to AI/ML development teams and support architectural decision-making.
• Review existing AI solutions and identify opportunities for performance, scalability, cost, and reliability improvements.
• Lead the deployment of AI solutions using cloud platforms, Docker, APIs, and production infrastructure.
• Ensure development follows appropriate coding standards, security practices, architecture principles, and deployment guidelines.
• Stay updated with emerging technologies in GenAI, LLMs, Agentic AI, MCP, RAG, and AI orchestration frameworks.