Nagarro

Staff Engineer, Generative AI

Nagarro
Apply
12 hours ago
Remote, IndiaStaff+

Responsibilities

  • Understand client business use cases and technical requirements and translate them into technical designs.
  • Architect and implement scalable GenAI and agentic AI solutions end to end.
  • Define technologies, patterns, frameworks, guidelines, benchmarks, and non-functional requirements for implementations.
  • Write and review architecture and high-level design documents for developers.
  • Review architecture and designs for extensibility, scalability, security, design patterns, user experience, and non-functional requirements.
  • Develop production-ready Python systems, APIs, RAG solutions, and cloud deployments on Azure or AWS.
  • Map technical decisions to requirements and communicate them to developers and cross-functional teams.
  • Identify and evaluate alternative solutions and select options that meet client requirements.
  • Analyze and resolve code and review issues through systematic root-cause investigation.
  • Conduct proofs of concept to validate proposed designs and technologies.

Requirements

  • 6+ years of total experience.
  • Bachelor’s or master’s degree in computer science, information technology, or a related field.
  • Deep understanding of LLMs, including GPTs, Llama, Claude, Gemini, Qwen, Mistral, and BERT-family models, and Transformer architectures.
  • Expert prompt engineering skills and proven experience implementing RAG architectures.
  • High proficiency in Python and AI/ML libraries including LangChain, LlamaIndex, LangGraph, LangSmith, Hugging Face Transformers, Scikit-learn, PyTorch, or TensorFlow.
  • Strong experience with fine-tuning, distillation, evaluation, and GenAI evaluation metrics such as BLEU, ROUGE, perplexity, semantic similarity, and human evaluation.
  • Experience using managed AI/ML services such as Azure Machine Learning Studio or AI Foundry and deploying production AI systems on Azure or AWS.
  • Strong understanding of vector databases such as Weaviate and Neo4j.
  • Ability to build and expose APIs with FastAPI and integrate databases through an ORM such as SQLAlchemy or Tortoise ORM.
  • Strong Python programming skills and the ability to produce clean, efficient, maintainable, production-ready code with strong testing practices.
  • Experience scaling AI solutions for enterprise workloads and live production environments.
  • Successful delivery of at least one production GenAI or agentic AI solution.
  • Familiarity with Model Context Protocol (MCP).
  • Contributions to open-source GenAI projects.
  • Experience with React or other JavaScript frameworks for user-facing interfaces and front-end integrations is preferred.
  • Excellent communication and cross-functional collaboration skills.

Tech Stack

AWSAzureFastAPIHugging Face TransformersJavaScriptNeo4jPythonPyTorchReactscikit-learnTensorFlow
Nagarro

About Nagarro

10,000+ employees

Nagarro provides digital engineering and IT consulting services to enterprises, delivering custom software development, cloud modernization, data and analytics, IoT, and digital commerce solutions. Its business model centers on project-based and managed services across the full product lifecycle, from strategy and design to build and operations. Nagarro is a public company headquartered in Munich and listed on the Frankfurt Stock Exchange, with global delivery across multiple regions.

Contact me