Senior Staff Engineer (GenAI, Langchain + Langraph, Machine Learning)

Nagarro; Bengaluru; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Nagarro Bengaluru is seeking senior AI professionals to design, develop, and deploy enterprise-grade Generative AI and Agentic AI solutions. You will lead projects that push LangChain, LangGraph, and related ecosystem tools in scalable, production environments.

You will craft advanced RAG architectures, manage memory systems, and optimize prompts, while collaborating with engineering, architecture, and product teams to deliver real business impact.

Qualifications

• 7.5 to 12 years of overall experience in Data Science, ML, and AI.
• Strong hands-on experience with Generative AI fundamentals, LLMs, and Agentic AI systems.
• Proven expertise in developing GenAI applications using LangChain, LangGraph, and ecosystem tools.
• Experience designing Retrieval Augmented Generation (RAG) solutions, including retrieval, reranking, chunking, memory management, and context optimization.
• Strong understanding of prompt engineering techniques, including instruction tuning, ReAct frameworks, reasoning strategies, planning loops, and self-reflection mechanisms.
• Hands-on experience with LLM evaluation frameworks, model assessment, and GenAI quality measurement methodologies.
• Experience using LangSmith for tracing, monitoring, debugging, evaluation, regression testing, and performance optimization of GenAI applications.
• Strong knowledge of Vector Databases and Embeddings, including FAISS, Azure AI Search, OpenSearch, PGVector, or similar technologies.
• Experience building intelligent agents, tool-calling agents, planner-executor frameworks, multi-agent systems, and hierarchical agent architectures.
• Good understanding of memory architectures, including episodic memory, semantic memory, and long-term vector-based memory systems.
• Experience integrating AI agents with APIs, enterprise applications, knowledge repositories, and external tools.
• Strong foundation in classical Machine Learning concepts, including feature engineering, model development, hyperparameter tuning, and model evaluation.
• Experience working with structured and unstructured datasets for predictive and analytical use cases.
• Understanding of MLOps concepts, including model monitoring, data drift detection, concept drift analysis, and model quality management.
• Hands-on experience with cloud platforms such as AWS, Azure, or Databricks.
• Proficiency with version control systems and collaborative development tools such as Git and GitHub.
• Strong problem-solving, analytical, communication, and stakeholder management skills.
• Candidate should have an official notice period of 30 days or less and must be able to join within one month.

Responsibilities

• Design, develop, and deploy enterprise-grade Generative AI and Agentic AI solutions using modern LLM frameworks and tools.
• Build scalable GenAI applications leveraging LangChain, LangGraph, and related ecosystem technologies.
• Design and implement advanced RAG architectures to improve response quality, grounding, and knowledge retrieval accuracy.
• Develop and optimize prompt engineering strategies to enhance reasoning, planning, tool usage, and response generation capabilities.
• Build intelligent agents capable of tool calling, workflow orchestration, task planning, and autonomous decision-making.
• Develop multi-agent systems and agent collaboration frameworks for complex business workflows.
• Implement memory-driven agent architectures supporting contextual awareness and long-term knowledge retention.
• Create evaluation frameworks to measure performance, reliability, robustness, and business effectiveness of AI solutions.
• Establish monitoring, tracing, testing, and observability frameworks using LangSmith and related tools.
• Build and integrate Model Context Protocol (MCP) based services and external tool integrations.
• Enable AI systems to interact with APIs, applications, code execution environments, and enterprise knowledge sources.
• Apply Machine Learning techniques to solve business problems involving structured and unstructured data.
• Perform model development, feature engineering, model optimization, validation, and performance analysis.
• Collaborate closely with engineering, architecture, and cross-functional teams to productionize AI and ML solutions.
• Ensure scalability, security, maintainability, and reliability of AI-powered applications.
• Support MLOps initiatives, including model monitoring, drift detection, performance tracking, and continuous improvement.
• Maintain comprehensive technical documentation, coding standards, and quality assurance practices throughout the development lifecycle.
• Stay current with emerging trends, frameworks, tools, and best practices in Generative AI, Agentic AI, Machine Learning, and AI Engineering.

Skills

Generative AI

LLMs

LangChain

LangGraph

Agentic AI

RAG architectures

Memory architectures

Prompt engineering

Vector databases

MLOps

APIs & tool integration

ML concepts

Tools

LangSmith

FAISS

Azure AI Search

OpenSearch

PGVector

Job description

We're Nagarro.

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 a scale across all devices and digital mediums, and our people exist everywhere in the world (18000+ experts across 36 countries, to be exact). Our work culture is dynamic and non-hierarchical. We are looking for great new colleagues. That is where you come in!

Requirements

• 7.5 to 12 years of overall experience in Data Science, Machine Learning, and Artificial Intelligence.
• Strong hands-on experience with Generative AI fundamentals, Large Language Models (LLMs), and Agentic AI systems.
• Proven expertise in developing GenAI applications using LangChain, LangGraph, and associated ecosystem tools.
• Experience designing and implementing Retrieval Augmented Generation (RAG) solutions, including retrieval, reranking, chunking, memory management, and context optimization.
• Strong understanding of prompt engineering techniques, including instruction tuning, ReAct frameworks, reasoning strategies, planning loops, and self-reflection mechanisms.
• Hands-on experience with LLM evaluation frameworks, model assessment, and GenAI quality measurement methodologies.
• Experience using LangSmith for tracing, monitoring, debugging, evaluation, regression testing, and performance optimization of GenAI applications.
• Strong knowledge of Vector Databases and Embeddings, including FAISS, Azure AI Search, OpenSearch, PGVector, or similar technologies.
• Experience building intelligent agents, tool-calling agents, planner-executor frameworks, multi-agent systems, and hierarchical agent architectures.
• Good understanding of memory architectures, including episodic memory, semantic memory, and long-term vector-based memory systems.
• Experience integrating AI agents with APIs, enterprise applications, knowledge repositories, and external tools.
• Strong foundation in classical Machine Learning concepts, including feature engineering, model development, hyperparameter tuning, and model evaluation.
• Experience working with structured and unstructured datasets for predictive and analytical use cases.
• Understanding of MLOps concepts, including model monitoring, data drift detection, concept drift analysis, and model quality management.
• Hands-on experience with cloud platforms such as AWS, Azure, or Databricks.
• Proficiency with version control systems and collaborative development tools such as Git and GitHub.
• Strong problem-solving, analytical, communication, and stakeholder management skills.
• Candidate should have an official notice period of 30 days or less and must be able to join within one month.

Responsibilities

• Design, develop, and deploy enterprise-grade Generative AI and Agentic AI solutions using modern LLM frameworks and tools.
• Build scalable GenAI applications leveraging LangChain, LangGraph, and related ecosystem technologies.
• Design and implement advanced RAG architectures to improve response quality, grounding, and knowledge retrieval accuracy.
• Develop and optimize prompt engineering strategies to enhance reasoning, planning, tool usage, and response generation capabilities.
• Build intelligent agents capable of tool calling, workflow orchestration, task planning, and autonomous decision-making.
• Develop multi-agent systems and agent collaboration frameworks for complex business workflows.
• Implement memory-driven agent architectures supporting contextual awareness and long-term knowledge retention.
• Create evaluation frameworks to measure performance, reliability, robustness, and business effectiveness of AI solutions.
• Establish monitoring, tracing, testing, and observability frameworks using LangSmith and related tools.
• Build and integrate Model Context Protocol (MCP) based services and external tool integrations.
• Enable AI systems to interact with APIs, applications, code execution environments, and enterprise knowledge sources.
• Apply Machine Learning techniques to solve business problems involving structured and unstructured data.
• Perform model development, feature engineering, model optimization, validation, and performance analysis.
• Collaborate closely with engineering, architecture, and cross-functional teams to productionize AI and ML solutions.
• Ensure scalability, security, maintainability, and reliability of AI-powered applications.
• Support MLOps initiatives, including model monitoring, drift detection, performance tracking, and continuous improvement.
• Maintain comprehensive technical documentation, coding standards, and quality assurance practices throughout the development lifecycle.
• Stay current with emerging trends, frameworks, tools, and best practices in Generative AI, Agentic AI, Machine Learning, and AI Engineering.