Staff Engineer, LLM Application Frameworks

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 (17500+ experts across 39 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:

• Total Experience: 6+ years

  in Data Science / Applied Machine Learning, including

  12+ years in Generative AI / LLM-based solutions

  .• Strong proficiency in

  Python

  , with hands-on experience using

  LangChain, Pandas, NumPy, scikit-learn, Hugging Face Transformers, Pydantic

  , etc.• Experience deploying

  GenAI workloads on AWS

  , including

  Amazon Bedrock, SageMaker, Lambda, ECS, API Gateway, Step Functions, CloudWatch

  .• Deep understanding of

  LLM architectures

  , tokenization,

  RAG

  , embeddings, and vector databases such as

  FAISS, Qdrant, Pinecone, OpenSearch

  .• Hands-on experience implementing

  agent-based architectures

  and multi-step reasoning pipelines.• Strong expertise in

  data wrangling, feature engineering

  , and building ML models for

  classification, regression, clustering, and NLP

  .• Experience with

  CI/CD

  , API development, and integrating GenAI models into production-grade applications.• Familiarity with

  LangGraph, AutoGPT, CrewAI

  , or other custom agent frameworks.• Knowledge of vector databases such as

  Qdrant, Snowflake Cortex

  , embedding models, and custom

  RAG pipelines

  .• Prior contributions to

  open-source GenAI projects

  or research work in LLM/NLP domains.• Hands-on experience with

  MLOps

  , including model versioning and monitoring tools (

  MLflow, Weights & Biases, SageMaker Model Monitor

  ).• Exposure to

  fine-tuning and parameter-efficient tuning

  (LoRA, QLoRA) of LLMs.• Understanding of

  data privacy, PII redaction, security, and compliance

  considerations in GenAI applications.• Strong analytical thinking, problem-solving, and communication skills.

RESPONSIBILITIES:

• Build, deploy, and optimize

  Generative AI and LLM-based applications

  for scalable enterprise use cases.• Design and implement

  RAG systems

  , vector search pipelines, and agent-based reasoning workflows.• Architect and develop

  end-to-end ML/GenAI solutions

  including data ingestion, preprocessing, experimentation, evaluation, and deployment.• Work with cross-functional teams to define problem statements and translate business requirements into technical solutions.• Develop and maintain

  GenAI-powered APIs, microservices

  , and automation workflows using AWS services.• Optimize model performance, cost efficiency, token usage, prompt structures, and overall system reliability.• Build reusable

  GenAI components

  including prompt templates, toolchains, memory modules, evaluators, and monitoring dashboards.• Implement robust

  MLOps practices

  for version control, experiment tracking, CI/CD pipelines, and automated deployment.• Ensure high-quality production readiness through

  testing, model validation, drift detection, and continuous monitoring

  .• Conduct research, POCs, and benchmarking of emerging

  LLMs, embeddings, vector databases

  , and agent frameworks.• Prepare documentation, architecture diagrams, and best practices for internal and client-facing teams.• Collaborate with engineering, product, and cloud teams to ensure seamless integration of GenAI features into applications.• Mentor junior engineers and contribute to knowledge sharing, code reviews, and innovation initiatives.• Ensure compliance with

  security, privacy, and responsible AI

  guidelines across all GenAI implementations.