AI Architect/ Tech Lead

Zensar; Hyderabad, Pune District, Bengaluru; Hybrid; INR 4,200,000 - 6,600,000; Full time

Job summary

Zensar seeks an experienced software architect to shape its AI platform in Hyderabad. You will design multiagent orchestration, MCP-based context sharing, and scalable LLM integrations, ensuring high throughput and low latency across enterprise tools.

You will mentor engineers, publish RFCs, and collaborate with product, security, and operations to drive performance tuning, RAG pipelines, and vector databases for production AI services.

Qualifications

• 10+ years of software architecture experience, incl. 3+ years building production-grade LLM apps.
• Deep expertise in multiagent frameworks such as LangGraph, AutoGen, or CrewAI.
• Experience designing or implementing MCP or similar context-sharing protocols.
• Strong command of Python, TypeScript, or Go and cloud-native technologies (AWS/GCP/Azure, Kubernetes, Docker).
• Hands-on experience with prompt engineering, Retrieval-Augmented Generation (RAG) pipelines, and vector databases.
• Proven ability to produce high-quality, production-ready code and prototypes.
• Outstanding verbal and written communication skills, with a track record of leading technical discussions.
• Experience authoring architecture RFCs and establishing engineering standards.
• Ability to translate complex AI concepts into actionable solutions for business stakeholders.

Responsibilities

• Design and implement multiagent orchestration frameworks for autonomous negotiation, task delegation, and state management.
• Architect and develop scalable Model Context Protocol (MCP) servers and clients for secure LLM integration with data sources and enterprise tools.
• Define the architectural vision for Zensar's internal AI platform, ensuring high throughput, low latency, and seamless developer workflows.
• Write production-ready code, build prototypes, and establish engineering best practices for AI application development.
• Standardize architectural patterns across the organization and author comprehensive RFCs.
• Mentor junior engineers and foster a culture of technical excellence.
• Collaborate with product, security, and operations teams to align AI solutions with business goals.
• Evaluate and integrate emerging AI SDKs, vector databases, and RAG pipelines.
• Drive performance tuning, scalability testing, and reliability engineering for AI services.
• Communicate complex technical concepts clearly to both technical and nontechnical stakeholders

Skills

Multiagent frameworks

MCP / context sharing

Python

TypeScript

Go

Cloud-native

RAG pipelines

Vector databases

LLM production

Leadership & communication

Education

Bachelor's or higher in Computer Science / Engineering

Tools

LangGraph

AutoGen

CrewAI

Job description

• Design and implement multiagent orchestration frameworks for autonomous negotiation, task delegation, and state management.
• Architect and develop scalable Model Context Protocol (MCP) servers and clients for secure LLM integration with data sources and enterprise tools.
• Define the architectural vision for Zensar's internal AI platform, ensuring high throughput, low latency, and seamless developer workflows.
• Write productionready code, build prototypes, and establish engineering best practices for AI application development.
• Standardize architectural patterns across the organization and author comprehensive RFCs.
• Mentor junior engineers and foster a culture of technical excellence.
• Collaborate with product, security, and operations teams to align AI solutions with business goals.
• Evaluate and integrate emerging AI SDKs, vector databases, and RAG pipelines.
• Drive performance tuning, scalability testing, and reliability engineering for AI services.
• Communicate complex technical concepts clearly to both technical and nontechnical stakeholders

• 10+ years of software architecture experience, with at least 3 years building productiongrade LLM applications.
• Deep expertise in multiagent frameworks such as LangGraph, AutoGen, or CrewAI.
• Proven experience designing or implementing Model Context Protocol (MCP) or similar contextsharing protocols.
• Strong command of Python, TypeScript, or Go and cloudnative technologies (AWS/GCP/Azure, Kubernetes, Docker).
• Handson experience with prompt engineering, RetrievalAugmented Generation (RAG) pipelines, and vector databases.
• Demonstrated ability to produce highquality, productionready code and prototypes.
• Outstanding verbal and written communication skills, with a track record of leading technical discussions.
• Experience authoring architecture RFCs and establishing engineering standards.
• Ability to translate complex AI concepts into actionable solutions for business stakeholders.
• Bachelors or higher degree in Computer Science, Engineering, or a related field.