New opportunity

Sr Architect

Birlasoft Limited · Hyderabad, India

About this role

The Sr Architect (Mern GEN AI Architect) will lead the architecture, design, and development of enterprise-grade Generative AI and Agentic AI solutions. This role requires a seasoned technology leader to drive AI transformation initiatives from concept to production deployment. Responsibilities include designing multi-agent systems, developing scalable AI applications using LLMs and RAG, building backend services with Python, and creating intuitive user interfaces with React.js. The architect will also design cloud-native solutions on AWS and define engineering standards and governance. Key Responsibilities: Lead architecture and development of enterprise-grade Generative AI and Agentic AI solutions. Design multi-agent systems using frameworks like CrewAI, AutoGen, LangGraph, LangChain, Semantic Kernel, and LlamaIndex. Develop scalable AI applications leveraging LLMs, RAG, and Agentic Workflows. Build robust backend services using Python (FastAPI, Flask, Django) and user interfaces using React.js, TypeScript, and Redux. Architect cloud-native AI solutions on AWS (Bedrock, Lambda, ECS, EKS, SageMaker, OpenSearch, DynamoDB, S3). Manage and mentor large engineering teams, conduct architecture and code reviews, and engage with CXO-level stakeholders. Required Qualifications: 18–23 years of experience in designing and delivering enterprise-scale digital solutions. Strong expertise in Python (10+ years), React, Agentic AI frameworks, and AWS Cloud. Hands-on experience with MERN stack (MongoDB, Express.js, React.js, Node.js). Proven track record of architecting and implementing large-scale Generative AI applications. Ability to estimate project efforts and provide technical leadership during pre-sales engagements.

For full details about this role, click “Apply on company site” to view the employer’s original posting.

Skills for this role

Generative AIAgentic AIMERN StackAWS CloudPythonReact.jsCrewAIAutoGenLangGraphLangChainSemantic KernelLlamaIndexFastAPIFlaskDjangoTypeScriptReduxAmazon BedrockAWS LambdaAmazon SageMakerMongoDBExpress.jsNode.js

Checking your profile…

Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.

Understand the role

What matters most

Architecting Multi-Agent AI Systems
The role centers on designing and deploying complex, enterprise-grade agentic workflows using frameworks like CrewAI, AutoGen, and LangGraph. You must demonstrate how to orchestrate multiple autonomous agents to solve business problems while ensuring scalability and reliability within an AWS cloud environment.
Full-Stack AI Transformation Leadership
You are expected to bridge the gap between advanced AI backends (Python, RAG, LLMs) and intuitive front-end interfaces (React, TypeScript). Success requires defining engineering standards that govern both the AI orchestration layer and the traditional MERN stack components.
Pre-sales and CXO Stakeholder Management
Beyond technical design, you must act as a strategic advisor. This involves estimating project efforts, articulating the value of AI transformation to non-technical executives, and providing technical leadership during the pre-sales phase to secure and define new initiatives.

Likely challenges to think through

Balancing Rapid AI Innovation with Enterprise Governance
The fast-evolving nature of Agentic AI frameworks often conflicts with the need for stable, secure, and maintainable enterprise architecture. Prepare to discuss how you implement governance, code review standards, and security protocols without stifling the agility required for GenAI development.
Complexity of Multi-Agent Orchestration
Designing systems where multiple agents interact introduces non-deterministic behaviors and debugging difficulties. Prepare to explain your approach to monitoring, logging, and error handling in agentic workflows to ensure production-grade stability.

Practice your answers

Technical practice

Designing Multi-Agent Systems

What to coverDiscuss the trade-offs between using frameworks like CrewAI, AutoGen, or LangGraph for orchestrating multi-agent workflows. Focus on how you manage agent communication, state persistence, and error handling in complex, non-deterministic AI systems.

RAG Architecture and Optimization

What to coverExplain your approach to building scalable RAG pipelines, specifically addressing document chunking strategies, vector database selection (e.g., OpenSearch), and retrieval accuracy. Suggestion: Prepare to discuss how you handle latency and context window limitations when integrating Amazon Bedrock.

Python Backend Scalability

What to coverGiven the requirement for high-performance backend services, compare the use of FastAPI versus Django for AI-heavy applications. Highlight your experience with asynchronous programming and microservices architecture to ensure non-blocking AI inference.

AWS Cloud-Native AI Deployment

What to coverDescribe how you would architect a production-grade AI solution using AWS SageMaker and EKS. Address how you ensure security, cost-efficiency, and high availability when deploying LLM-based services.

MERN Stack Integration with AI

What to coverExplain how you integrate Node.js/Express backend services with Python-based AI microservices in a MERN stack environment. Discuss the communication protocols and data synchronization strategies you prefer.

Engineering Standards and Governance

What to coverHow do you define and enforce coding standards and architecture governance across large, distributed engineering teams? Suggestion: Focus on your process for conducting effective architecture reviews and ensuring technical debt is managed during rapid AI development.

AI-Powered UI/UX Development

What to coverDiscuss the challenges of building intuitive user interfaces for Agentic AI applications using React and TypeScript. Focus on how you handle streaming responses, real-time feedback, and complex state management with Redux.

Pre-sales and Effort Estimation

What to coverHow do you approach estimating the effort for complex, high-uncertainty GenAI projects during pre-sales? Explain how you balance client expectations with the technical realities of AI model performance and data readiness.

Behavioural practice

Leading AI Transformation

What to coverDescribe a situation where you led an organization through a significant technology shift, such as adopting GenAI. Focus on how you managed stakeholder expectations and addressed technical resistance from the team.

Mentoring Large Engineering Teams

What to coverProvide an example of how you have mentored senior engineers or led large teams to improve their technical output. Detail the specific actions you took to foster a culture of continuous learning and high-quality engineering.

Engaging with CXO Stakeholders

What to coverShare an experience where you had to explain a complex technical AI strategy to non-technical executive leadership. How did you translate technical risks and benefits into business value?

Managing Project Failure or Pivot

What to coverDescribe a time when an AI project did not meet its initial performance goals or requirements. Explain the steps you took to diagnose the issue, communicate the situation, and pivot the strategy to achieve a successful outcome.

Sharpen your knowledge

Topics to prepare

Multi-Agent System Architecture
Review the conceptual differences between single-LLM applications and multi-agent orchestration. Exercise: Draft a high-level architecture diagram for a RAG-based system that uses specialized agents for document retrieval, synthesis, and verification using frameworks like LangGraph or CrewAI. This is critical for the role's focus on designing enterprise-grade Agentic AI solutions.
Enterprise AI Governance and Standards
Study best practices for AI model deployment, including security, cost management, and performance monitoring in production. Exercise: Outline a governance framework for deploying LLMs on AWS Bedrock, focusing on data privacy, latency optimization, and model versioning. This aligns with the requirement to define engineering standards and lead AI transformation initiatives.

Skills to revise

Agentic Framework Implementation
Gain hands-on experience with LangChain, LangGraph, or AutoGen. Exercise: Build a small-scale prototype that uses an agent to perform a multi-step task, such as fetching data from an API and summarizing it based on specific constraints. This directly addresses the requirement for designing multi-agent systems.
AWS Cloud-Native AI Deployment
Practice deploying AI services using AWS infrastructure. Exercise: Create a serverless pipeline using AWS Lambda and Amazon Bedrock to process text inputs and store results in DynamoDB. This is essential for the role's responsibility to architect cloud-native AI solutions.
Python Backend Development for AI
Focus on building scalable APIs with FastAPI. Exercise: Develop a RESTful API in FastAPI that integrates with an LLM and handles asynchronous requests. This is relevant to the requirement for building robust backend services for AI applications.

Your preparation checklist

Prepare a Multi-Agent System Architecture Case Study
Develop a high-level architectural diagram and narrative for a complex enterprise AI solution. Focus on how you integrated frameworks like LangGraph or CrewAI with RAG pipelines on AWS, specifically addressing how you managed agent orchestration, state persistence, and latency in a production environment.
Document Your Python and MERN Stack Leadership Experience
Create a summary of your experience leading teams through the full software development lifecycle using Python (FastAPI/Django) and the MERN stack. Highlight specific instances where you defined engineering standards, performed code reviews, and mentored developers to improve code quality and system scalability.
Outline an AWS Cloud-Native AI Deployment Strategy
Prepare a technical overview of how you would deploy a Generative AI application using AWS Bedrock, SageMaker, and EKS. Include your approach to security, cost optimization, and governance when managing enterprise-grade AI models in a cloud environment.
Formulate Strategic Questions for CXO Stakeholders
Draft a list of high-level questions regarding the company's AI transformation roadmap, such as how they prioritize AI use cases for pre-sales engagements, their current challenges with AI governance, and how they measure the ROI of Agentic AI initiatives.
Refine Your Pre-Sales and Estimation Methodology
Prepare to discuss your process for estimating project efforts for large-scale digital transformations. Be ready to explain how you balance technical feasibility with business requirements when presenting solutions to non-technical stakeholders or clients.

Availability last checked: 18 Oct 2026. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy

KEEP EXPLORING

Similar AI jobs

Related skills and specializations in India. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…