Senior Staff Engineer

Nagarro; India; On-site; INR 4,000,000 - 6,000,000; Full time

Job summary

Nagarro is seeking an experienced GenAI/Agentic AI architect to design and implement end-to-end GenAI solutions. You will work on scalable architectures, production-grade Python code, and API delivery on cloud platforms such as Azure or AWS.

You will collaborate with product and engineering teams to translate business needs into AI-driven solutions, apply prompt engineering, RAG patterns, and model evaluation to deliver enterprise-grade results.

Qualifications

• Total experience 8+ years in AI/GenAI.
• Deep understanding of LLM architectures and Transformers.
• Expert-level prompt engineering and RAG implementation experience.
• Proficiency in Python and AI/ML libraries such as LangChain, LlamaIndex, and Transformers.
• Experience in fine-tuning, distillation, and evaluation of GenAI models.
• Experience deploying GenAI on Azure or AWS and exposing APIs via FastAPI.
• Strong knowledge of vector databases and GenAI evaluation metrics.
• Strong collaboration across product and engineering teams.

Responsibilities

• Architect and implement end-to-end GenAI and Agentic AI solutions.
• Translate client requirements into technical designs and implementations.
• Develop scalable GenAI architectures with reliable production-grade code.
• POCs to validate design choices and technologies.
• Review and enforce non-functional requirements (NFRs) for projects.
• Collaborate with cross-functional teams to deliver AI-driven solutions.

Skills

LLMs

Prompt engineering

RAG patterns

Python

LangChain

LlamaIndex

PyTorch/TensorFlow

Azure/AWS

Vector databases

MCP

Open-source contributions

React (front-end)

Education

Bachelor’s or Master’s in CS/IT

Tools

LangChain

LlamaIndex

Weaviate

Neo4j

Hugging Face Transformers

PyTorch

TensorFlow

Azure ML

AWS

SQLAlchemy/Tortoise ORM

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 scale — across all devices and digital mediums, and our people exist everywhere in the world (18000+ experts across 40 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!

Company 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 scale — across all devices and digital mediums, and our people exist everywhere in the world (18000+ experts across 40 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 8+ years.
• Deep understanding of LLMs (e.g., GPTs, Llama, Claude, Gemini, Qwen, Mistral, BERT-family models) and their architectures (Transformers)
• Should have expert-level prompt engineering skills and proven experience implementing RAG patterns
• High proficiency in Python and standard AI/ML libraries (e.g., LangChain, LlamaIndex, LangGraph, LangSmith, Hugging Face Transformers, Scikit-learn, PyTorch/TensorFlow).
• Experience implementing RAG architectures and prompt engineering.
• Strong experience with fine-tuning and distillation techniques and evaluation.
• Strong experience using managed AI/ML services on the target cloud platform (e.g., Azure Machine Learning Studio, AI Foundry).
• Strong understanding of vector databases (e.g., Weaviate, Neo4j)
• understanding of GenAI evaluation metrics (e.g., BLEU, ROUGE, perplexity, semantic similarity, human evaluation).
• Architect and implement scalable GenAI and Agentic AI solutions end-to-end.
• Should be able to write high-quality, production-ready Python code with strong testing and maintainability practices.
• Should be able to productionize AI systems on Azure or AWS, ensuring enterprise-grade reliability and performance.
• Should be able to build and expose APIs using FastAPI, integrating with databases through an ORM.
• Should be able to scale GenAI solutions to support enterprise workloads.
• Collaborate across product and engineering teams to convert business needs into AI-driven solutions.
• Strong ability to both architect and code GenAI/Agentic AI solutions.
• Proven production experience with GenAI deployments on Azure or AWS.
• Strong experience in scaling AI solutions in live environments.
• Very strong Python programming skills with a track record of clean, efficient, and maintainable code.
• Should have successfully delivered at least one production GenAI/Agentic AI solution.
• Must have proficiency with FastAPI and at least one ORM (e.g., SQLAlchemy, Tortoise ORM).
• Should have familiarity with Model Context Protocol (MCP).
• Should have contributions to open-source GenAI projects.
• Good to have experience with React (or some other JS frameworks) for building user-facing interfaces and front-end integrations
• Excellent communication skills and the ability to collaborate effectively with cross-functional teams.

RESPONSIBILITIES

• Understanding the client’s business use cases and technical requirements and be able to convert them into technical design which elegantly meets the requirements.
• Mapping decisions with requirements and be able to translate the same to developers.
• Identifying different solutions and being able to narrow down the best option that meets the clients’ requirements.
• Defining guidelines and benchmarks for NFR considerations during project implementation.
• Writing and reviewing design document explaining overall architecture, framework, and high-level design of the application for the developers.
• Reviewing architecture and design on various aspects like extensibility, scalability, security, design patterns, user experience, NFRs, etc., and ensure that all relevant best practices are followed.
• Developing and designing the overall solution for defined functional and non-functional requirements; and defining technologies, patterns, and frameworks to materialize it.
• Understanding and relating technology integration scenarios and applying these learnings in projects.
• Resolving issues that are raised during code/review, through exhaustive systematic analysis of the root cause, and being able to justify the decision taken.
• Carrying out POCs to make sure that suggested design/technologies meet the requirements.

Qualifications

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