AI Architect

Experience in practicing Design Thinking and System Thinking approaches in real world scenarios.

Experience of working in an agile ecosystem with 100+ team members.

Experience in Technology leadership Role for large-scale delivery program.

Experience in leading proactive technology driven programs intended for proof of concepts, innovation, and solution assets development.

Experience in analysis, implementation and evaluation of IT systems and their specifications, good understanding of breadth & depth of technologies.

Experience in multiple technologies including Java, J2EE, JavaScript, Spring, Hibernate, web-services, .NET Framework, .NET Core, WEB API, Angular, ExtJS, Node JS, Python, Big Data, Cloud services etc.

Experience in design and implementation of Microservices, SOA, modern web apps and data driven solutions in a cloud native ecosystem.

A clear understanding of AWS / Azure cloud services & deployment models

Experience with IaaS & PaaS Platforms and SaaS based Service Offerings

A strong technical aptitude and ability to quickly learn new technologies.

Excellent analytical, inter-personal, and communication skills.

Excellent team player with problem-solving and trouble-shooting capabilities.

Experience developing and implementing enterprise IT strategy for clients.

Expert level of knowledge and hands on experience in App Development

Experience in API design, API development & Management

Hands on experience in DB design, Database architecture and optimization

Good knowledge of Data Strategy, Big Data and Machine Learning concepts

Leadership

Excellent organizational and leadership skills

Experience in controlling information technology budget.

Proven experience as IT director or similar role

Communication

Ability to communicate technology in an easy-to-understand way

Outstanding communication abilities

Experience in client communication and working with client on requirements and delivery.

Other skills

Strategic thinking & Problem-solving aptitude

AI & Agentic Engineering Expertise (Mandatory)

 Agentic Engineering Models

- Deep understanding of AI-led SDLC — how AI agents participate in planning, coding, review, testing, and deployment phases

- Experience designing multi-agent systems with defined roles (orchestrator, coder, reviewer, tester agents), task routing, and state management

- Familiarity with agent frameworks: Claude Agents SDK, or equivalent

  GenAI Developer Tooling (Hands-On)

- Direct experience using and configuring:

- Claude Code (Anthropic) — CLI-driven agentic coding, MCP server setup, custom slash commands, hooks, and CLAUDE.md context engineering

- Ability to configure, extend, and govern these tools at enterprise scale

  MCP & Agent Orchestration

- Experience with MCP (Model Context Protocol) — designing and deploying MCP servers to expose tools, APIs, and data sources to AI agents

- Understanding of tool use / function calling patterns for LLM-driven agents

- Familiarity with prompt chaining, RAG pipelines, and context window management strategies

 Prompt & Context Engineering

- Proficiency in prompt engineering — system prompts, few-shot examples, chain-of-thought, and structured output design

- Experience building context engineering frameworks — CLAUDE.md / Copilot instructions files, knowledge fabric design, and retrieval-augmented generation for code-aware agents

- Understanding of model evaluation — benchmarking GenAI output quality for coding and testing tasks

Tooling & Platform Strategy

    - Claude Code (Anthropic) — agentic coding, file-level reasoning, and CLI-driven automation

Engineering Enablement

 - Build and operationalize:

   - Scaffolding frameworks for requirements drafting, code generation, and test automation

   - AI accelerators for synthetic data generation, intelligent regression, and defect prediction

   - Context engineering pipelines — managing prompts, embeddings, knowledge graphs, and retrieval-augmented generation (RAG) for code-aware AI agents

 - Configure and govern MCP (Model Context Protocol) servers and tool integrations to extend agent capabilities across enterprise systems

Governance & Standards

 - Establish AI usage governance covering prompt standards, context security, model selection criteria, and output quality controls

 - Define guardrails for responsible AI use in engineering — IP protection, hallucination mitigation, and compliance alignment

 - Build and maintain AI engineering playbooks, runbooks, and standards for adoption at scale