Staff Engineer, Generative AI Engineer

Nagarro1; India; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Nagarro is seeking an experienced AI/GenAI engineer in India to design, develop, and deploy enterprise-grade AI agents and multi-agent systems using Python and FastAPI. You will build scalable RAG-based solutions, optimize prompts and retrieval strategies, and integrate agents with REST APIs across enterprise apps.

The role requires deep knowledge of LLMs, vector databases, embeddings, and security, with CI/CD expertise and a focus on production readiness and governance.

Qualifications

• Total experience 5.5+ years with strong recent experience in AI/GenAI engineering.

Responsibilities

• Design, develop, and deploy enterprise-grade AI agents, Agentic AI, and conversational AI solutions using Python and FastAPI.
• Build and manage multi-agent systems, including workflow orchestration, reasoning, memory, tool integration, and agent coordination.
• Design and implement scalable RAG-based AI solutions using vector databases, embeddings, and advanced prompt engineering techniques.
• Develop and optimize LLM prompts, retrieval strategies, agent workflows, and AI responses for accuracy, reliability, and business relevance.
• Integrate AI agents with enterprise applications using REST APIs, MCP, and A2A protocols.
• Implement secure and scalable cloud-native AI applications with OAuth2/JWT, Key Vault, Responsible AI guardrails, and governance controls.
• Build and maintain CI/CD pipelines using Azure DevOps, Docker, Kubernetes, Argo CD, and GitOps practices.
• Establish automated testing, observability, monitoring, logging, tracing, and AI evaluation using tools such as LangSmith, OpenTelemetry, and Elasticsearch.
• Optimize AI solutions for performance, scalability, reliability, latency, cost efficiency, and production readiness.
• Collaborate with business, platform, security, cloud, and engineering teams to deliver enterprise-grade AI solutions.
• Evaluate and adopt emerging LLMs, Agentic AI frameworks, AI engineering tools, and industry best practices.
• Provide technical leadership and mentor engineering teams on GenAI, LLM applications, RAG, agent architecture, and production AI engineering.

Skills

Python

GenAI engineering

API development

LLMs

Prompt engineering

RAG

Vector databases

Embeddings

Agent orchestration

Stakeholder management

Communication

Problem solving

Education

Bachelor's or Master's in CS/IT or related field

Tools

FastAPI

LangGraph

CrewAI

Temporal

Docker

Kubernetes

CI/CD

Azure DevOps

Argo CD

GitOps

LangSmith

OpenTelemetry

Elasticsearch

Azure OpenAI

AWS Bedrock

Job description

Requirements

• Total experience: 5.5 + years , with strong recent experience in AI/GenAI engineering .
• Strong hands‑on experience with Python and production‑grade AI/GenAI application development.
• Must-have expertise in FastAPI for developing scalable, secure, and production-ready APIs.
• Strong experience with LLMs, Prompt Engineering, RAG, Vector Databases, and Embeddings .
• Hands‑on experience designing and developing enterprise AI agents, conversational AI, and Agentic AI solutions .
• Strong experience building RAG pipelines , including document processing, chunking, embeddings, vector search, retrieval, grounding, and response generation.
• Strong knowledge of Vector Databases and embedding technologies , with experience optimizing retrieval and relevance.
• Hands‑on experience with LangGraph, CrewAI, Temporal , or similar agent orchestration frameworks.
• Experience integrating AI agents with enterprise applications using REST APIs, MCP, and A2A protocols .
• Good understanding of Azure OpenAI, AWS Bedrock, or other enterprise LLM platforms .
• Experience with Docker, Kubernetes, CI/CD, Azure DevOps, Argo CD, and GitOps practices.
• Strong understanding of AI security, OAuth2/JWT, Responsible AI guardrails, governance, and enterprise application security .
• Experience with AI evaluation, observability, monitoring, logging, and tracing , using tools such as LangSmith, OpenTelemetry, or Elasticsearch.
• Good‑to‑have experience with Semantic Kernel, AWS Bedrock AgentCore , and enterprise AI governance.
• Strong analytical, problem-solving, stakeholder management, collaboration, and communication skills.
• Bachelor's or master's degree in computer science, Information Technology, or a related field.

Responsibilities

• Design, develop, and deploy enterprise‑grade AI agents, Agentic AI, and conversational AI solutions using Python and FastAPI .
• Build and manage multi‑agent systems , including workflow orchestration, reasoning, memory, tool integration, and agent coordination.
• Design and implement scalable RAG‑based AI solutions using vector databases, embeddings, and advanced prompt engineering techniques.
• Develop and optimize LLM prompts, retrieval strategies, agent workflows, and AI responses for accuracy, reliability, and business relevance.
• Integrate AI agents with enterprise applications using REST APIs, MCP, and A2A protocols .
• Implement secure and scalable cloud‑native AI applications with OAuth2/JWT, Key Vault, Responsible AI guardrails, and governance controls .
• Build and maintain CI/CD pipelines using Azure DevOps, Docker, Kubernetes, Argo CD, and GitOps practices.
• Establish automated testing, observability, monitoring, logging, tracing, and AI evaluation using tools such as LangSmith, OpenTelemetry, and Elasticsearch.
• Optimize AI solutions for performance, scalability, reliability, latency, cost efficiency, and production readiness .
• Collaborate with business, platform, security, cloud, and engineering teams to deliver enterprise‑grade AI solutions .
• Evaluate and adopt emerging LLMs, Agentic AI frameworks, AI engineering tools, and industry best practices .
• Provide technical leadership and mentor engineering teams on GenAI, LLM applications, RAG, agent architecture, and production AI engineering .