Senior Staff Engineer, Gen AI

Nagarro; India; Remote; INR 2,800,000 - 5,200,000; Full time

Job summary

Nagarro seeks a senior AI/ML backend engineer in India to design, build and deploy autonomous AI agents. You will orchestrate workflows with LangChain/LangGraph, integrate APIs and databases, and develop production-ready services using Python and Java.

You will focus on scalable, observable, cloud-native solutions with emphasis on prompt engineering, memory architectures and tool-use capabilities to drive business workflows.

Qualifications

• Total experience 7.5+ years.
• Strong experience in Python and Java development, coding and backend engineering.
• Hands-on experience with Microsoft Azure AI/ML and cloud-based AI solutions.
• Experience building and deploying AI agents for production environments.
• Strong experience with LLM application frameworks such as LangChain, LangGraph or equivalent.
• Experience with API development, integration, databases and external SaaS platforms.
• Experience with prompt engineering, agent orchestration, memory architectures and tool-use capabilities.
• Experience with scalable system design, distributed systems and asynchronous processing.
• Experience with CI/CD, containers, cloud-native deployment and production monitoring.
• Knowledge of observability, logging, debugging and AI agent evaluation frameworks.
• Strong understanding of LLM providers and modern AI developer tools.
• Excellent communication, collaboration and stakeholder management skills.

Responsibilities

• Design, develop and deploy autonomous AI agents capable of multi-step reasoning, planning and decision-making.
• Build and orchestrate agent workflows using LangChain, LangGraph and modern agent frameworks.
• Integrate AI agents with APIs, databases and SaaS platforms for end-to-end task execution.
• Develop prompt engineering strategies, memory architectures and tool-use capabilities.
• Build production-ready backend services and APIs using Python and Java.
• Deploy, monitor and maintain AI agents with focus on scalability, reliability and observability.
• Optimize AI agent performance across latency, cost and reliability.
• Debug, evaluate and continuously improve agent behavior through testing, logging and feedback loops.
• Implement cloud-native deployment, CI/CD, monitoring and production support capabilities.
• Collaborate with product, engineering and data teams to embed AI agents into business workflows.
• Evaluate emerging LLM technologies, agent frameworks and applied AI best practices.
• Provide technical guidance on AI agent architecture, integration and production adoption.

Skills

Python

Java

Azure AI/ML

LLM frameworks

API development

Distributed systems

CI/CD

Observability

Education

Bachelor’s or Master’s degree in CS/IT

Tools

LangChain

LangGraph

APIs

Job description

We are a Digital Product Engineering company that is scaling in a big way! We build products, services, and experiences that inspire, excite, and delight. We work at scale across all devices and digital mediums, and our people exist everywhere in the world (18,700 + experts across 39 countries, to be exact). Our work culture is dynamic and non-hierarchical. We're looking for great new colleagues. That's where you come in.

Job Description

REQUIREMENTS:

• Total experience 7.5+ years
• Strong experience in Python and Java development, coding and backend engineering
• Hands-on experience with Microsoft Azure AI/ML and cloud-based AI solutions
• Experience building and deploying AI agents for production environments
• Strong experience with LLM application frameworks such as LangChain, LangGraph or equivalent
• Experience with API development, integration, databases and external SaaS platforms
• Experience with prompt engineering, agent orchestration, memory architectures and tool-use capabilities
• Experience with scalable system design, distributed systems and asynchronous processing
• Experience with CI/CD, containers, cloud-native deployment and production monitoring
• Knowledge of observability, logging, debugging and AI agent evaluation frameworks
• Strong understanding of LLM providers and modern AI developer tools
• Excellent communication, collaboration and stakeholder management skills

RESPONSIBILITIES:

• Design, develop and deploy autonomous AI agents capable of multi-step reasoning, planning and decision-making
• Build and orchestrate agent workflows using LangChain, LangGraph and modern agent frameworks
• Integrate AI agents with APIs, databases and SaaS platforms for end-to-end task execution
• Develop prompt engineering strategies, memory architectures and tool-use capabilities
• Build production-ready backend services and APIs using Python and Java
• Deploy, monitor and maintain AI agents with focus on scalability, reliability and observability
• Optimize AI agent performance across latency, cost and reliability
• Debug, evaluate and continuously improve agent behavior through testing, logging and feedback loops
• Implement cloud-native deployment, CI/CD, monitoring and production support capabilities
• Collaborate with product, engineering and data teams to embed AI agents into business workflows
• Evaluate emerging LLM technologies, agent frameworks and applied AI best practices
• Provide technical guidance on AI agent architecture, integration and production adoption

Qualifications

Bachelor’s or master’s degree in computer science, Information Technology, or a related field.