1. Job Purpose

The Agentic AI Architect is responsible for defining and delivering the architecture for next-generation AI systems leveraging Large Language Models (LLMs), autonomous agents, and multi-agent orchestration frameworks to enable intelligent automation and advanced digital capabilities. This role focuses on designing scalable, secure, and production-ready AI platforms that support intelligent decision systems, conversational interfaces, automation workflows, and data-driven operational insights.

The Architect will collaborate closely with AI engineers, data engineers, platform teams, and product stakeholders to build enterprise-grade agentic AI systems aligned with organizational technology strategy, governance standards, and security policies.

1. Key Accountabilities

Strategic Activities
- Define enterprise architecture for agentic AI platforms, including multi-agent systems, orchestration frameworks, and LLM-driven applications.
- Design secure Function Calling interfaces and Tool Definition schemas to enable agents to interact with legacy systems, SQL databases, and enterprise CRMs.
- Architect Human-in-the-loop checkpoints and state-management protocols to ensure autonomous actions remain within defined operational guardrails.
- Drive adoption of Generative AI and autonomous agent systems across digital and operational platforms.
- Establish architecture standards for LLM pipelines, prompt engineering, evaluation frameworks, vector search, and Retrieval Augmented Generation (RAG).
- Design scalable AI inference architectures and microservices optimized for latency, cost efficiency, and reliability.
- Define governance frameworks ensuring responsible AI usage, security, explainability, and regulatory compliance.
- Contribute to the AI technology roadmap, including evaluation of new AI platforms, frameworks, and vendor solutions.
- Monitor emerging AI technologies and evaluate their potential impact and opportunities for the organization.
- Balance rapid innovation and experimentation with enterprise-grade reliability and operational stability.

Solution Architecture & Technical Leadership
- Architect end-to-end agentic AI systems including LLM orchestration layers, agent coordination mechanisms, and intelligent workflow automation.
- Design architectures integrating LLM inference services, vector databases, APIs, and enterprise data platforms.
- Define architectural patterns for multi-agent coordination, memory management, tool usage, and reasoning workflows.
- Develop reusable architectural frameworks and design patterns to accelerate AI solution development.




- Evaluate architecture alternatives and define trade-offs between performance, cost, scalability, and security.
- Provide technical guidance to engineering teams implementing AI-driven solutions.
- Ensure architectural alignment with enterprise architecture standards and cloud strategy.

Research & Emerging Technology Monitoring
- Track advancements in LLMs, agent frameworks, orchestration tools, reasoning engines, and AI infrastructure.
- Conduct research and experimentation to evaluate emerging AI technologies and frameworks.
- Develop prototypes and proof-of-concepts to validate architectural approaches.
- Document research findings and architectural guidance for internal knowledge sharing.
- Participate in AI technology communities and industry forums to remain current with evolving AI trends.

Systems & Software Design
- Design software components supporting agent orchestration, AI services, and inference pipelines.
- Produce architecture documentation covering system components, interfaces, and integration patterns.
- Develop multiple architectural views addressing both functional and non-functional requirements.
- Lead architecture and design reviews to ensure adherence to enterprise standards.

AI Platform Engineering & Integration
- Define and implement LLMOps / MLOps practices supporting model evaluation, monitoring, experimentation, and deployment.
- Establish observability frameworks for monitoring model performance, latency, reliability, and cost efficiency.
- Integrate AI services with enterprise applications through APIs, microservices, and data pipelines.
- Ensure production readiness of AI platforms through testing, monitoring, and performance optimization.

Team Leadership & Collaboration
- Provide architectural leadership to AI engineers, LLM engineers, and data engineers.
- Mentor engineering teams on AI architecture patterns, best practices, and design principles.
- Collaborate with product and business teams to translate requirements into scalable AI solutions.
- Support capability building and knowledge sharing across AI and engineering teams.
- Participate in recruitment and development of AI engineering talent.

1. Skills Required for the Role

AI & Machine Learning
- Strong expertise in machine learning,



generative AI, and large language models
- Experience designing LLM-based applications and agentic AI systems
- Hands-on experience with LangGraph, CrewAI, Autogen, or Semantic Kernel for multi-agent coordination.
- Experience in designing State Management and persistent memory systems (e.g., Zep, Mem0) for long-running autonomous tasks.
- Knowledge of prompt engineering, embeddings, vector databases, and RAG architectures
- Familiarity with AI orchestration frameworks and autonomous workflow design
- Experience implementing AI evaluation and monitoring frameworks

Programming & Engineering
- Strong programming skills in Python
- Experience with ML frameworks such as PyTorch, TensorFlow, or Keras
- Experience with data processing libraries (NumPy, Pandas, Scikit-learn)
- Ability to design scalable microservices and distributed systems
- Experience developing APIs and integration services

Cloud & AI Infrastructure
- Experience deploying AI solutions on cloud platforms (AWS, Azure, or GCP)
- Familiarity with containerization and orchestration (Docker, Kubernetes)
- Knowledge of vector databases, data pipelines, and AI infrastructure
- Experience with LLMOps / MLOps platforms

Architecture & System Design
- Expertise in distributed systems architecture
- Strong understanding of scalability, reliability, and performance engineering
- Ability to design enterprise-grade AI platforms and frameworks

Leadership & Communication
- Robust technical leadership and mentoring capabilities
- Excellent analytical and problem-solving skills
- Ability to communicate complex AI concepts to both technical and non-technical stakeholders
- Strong documentation and architecture communication skills

D. Educational and Experience Requirements

Minimum Education Requirements

Master's degree in computer science, AI/ML, or related field OR bachelor's degree

15+ years of total exp

10+ years' experience in distributed systems/ML

Minimum Requirement

Desired

Experience

- 10+ years in software architecture or ML engineering
- 3+ years hands-on experience with LLMs and generative AI
- Proven track record designing production AI systems at scale
- Experience with agent frameworks (LangGraph, CrewAI, Autogen, etc.)
- 10+ years in AI/ML systems architecture
- Experience in highly regulated industries (finance, healthcare, aviation)
- Prior experience with autonomous systems or robotics
- Published research or open-source contributions in agentic AI

Certifications
1. AWS Certified Machine Learning - Specialty
2. Azure AI Engineer Associate

📌 Agentic AI Architect (Gurugram)
🏢 Air India
📍 Gurugram