Staff Engineer, (Springboot Gen AI)

Nagarro SE

Job Overview

Location

Remote

Job Type

Full-time

Full Job Description

📋 Description

• You will architect and deliver cutting-edge, AI-powered enterprise solutions as a Staff Engineer at Nagarro, owning the full lifecycle of Spring Boot microservices that integrate Large Language Models (LLMs) into production-grade systems.
• Design and implement AI-orchestrated workflows using the Spring.AI framework—leveraging ChatClient, EmbeddingClient, and VectorStore abstractions—to enable conversational interfaces, semantic search, and Retrieval-Augmented Generation (RAG) capabilities that directly impact millions of end-users.
• Build resilient, horizontally scalable RESTful APIs with Spring Boot 3.x, Spring Data, and Spring Security, ensuring sub-second latency for AI-driven workloads while maintaining strict security, observability, and compliance standards.
• Integrate and manage multiple vector stores (Pinecone, Weaviate, pgvector) to power high-performance document retrieval and similarity search, optimizing embedding pipelines and indexing strategies for terabyte-scale datasets.
• Partner with product managers, UX researchers, and data scientists to refine prompts, manage prompt templates, and continuously improve model outputs—translating business requirements into robust technical solutions.
• Establish and evolve CI/CD pipelines using Docker and Kubernetes, automating the deployment, scaling, and monitoring of AI-enabled microservices across hybrid cloud environments (AWS, Azure, GCP).
• Champion best practices in secure data access, model governance, and responsible AI—implementing guardrails, audit trails, and rate-limiting strategies to protect sensitive enterprise data.
• Mentor senior and mid-level engineers, conducting architecture reviews, pair programming sessions, and knowledge-sharing workshops to elevate the team’s expertise in Java 17+, Spring ecosystem, and emerging Gen AI technologies.
• Continuously evaluate new LLM providers (OpenAI, Azure AI, Anthropic, open-source models) and benchmark performance, cost, and accuracy to recommend optimal model choices for each use case.
• Collaborate with DevOps and SRE teams to define SLIs/SLOs, implement auto-scaling policies, and ensure 99.9% uptime for mission-critical AI services.
• Drive technical debt reduction and modernization initiatives—refactoring legacy monoliths into cloud-native, event-driven architectures that accelerate feature delivery and reduce operational overhead.
• Contribute to Nagarro’s internal AI Center of Excellence by publishing whitepapers, speaking at meetups, and leading proof-of-concepts that shape the company’s Gen AI strategy.

🎯 Requirements

• 7+ years of hands-on Java development with deep expertise in Java 17 or higher, Spring Boot 3.x, Spring Data, and Spring Security.
• Proven experience with Spring.AI framework—specifically ChatClient, EmbeddingClient, and VectorStore abstractions—for building LLM-integrated applications.
• Production-level experience integrating and tuning vector stores such as Pinecone, Weaviate, or pgvector for document retrieval and similarity search.
• Solid understanding of LLM fundamentals (tokens, temperature, model architectures) and Retrieval-Augmented Generation (RAG) patterns.
• Familiarity with Docker, Kubernetes, and CI/CD pipelines for deploying and scaling AI-enabled microservices.

🏖️ Benefits

• Fully remote-first culture with flexible working hours and no micromanagement—work from anywhere in the world.
• Competitive compensation package with annual performance bonuses and stock options.
• Annual learning budget of $3,000 plus paid certifications (Spring, Kubernetes, AI/ML) to keep your skills cutting-edge.
• Comprehensive health, dental, and vision insurance for you and your dependents from day one.

Skills & Technologies

Java

Spring

Azure

Docker

Kubernetes

Senior

Remote

Ready to Apply?

Apply Externally

You will be redirected to an external site to apply.

Nagarro SE

Visit Website

About Nagarro SE

Nagarro SE is a publicly listed global digital engineering company headquartered in Munich, Germany. It provides strategy, experience design, cloud, data and AI, and platform modernization services to Fortune 500 and mid-market enterprises across banking, insurance, manufacturing and retail. Operating from more than 35 countries with 18,000+ employees, the company delivers agile, scalable solutions that accelerate digital transformation and improve time-to-market for clients worldwide.

View Company Profile