ABOUT THE ROLE :

As a Software Development Engineer at Stanza Living, you will build scalable, high-performance backend systems that power both core product experiences and AI-native applications. You will design robust architectures, build efficient APIs and workflows, and develop systems that can retrieve the right context, orchestrate tools, and automate complex tasks reliably in production.

This role is for engineers who are strong in backend fundamentals and are also comfortable building modern AI-powered systems using RAG, tool calling, and agentic workflows.

RESPONSIBILITIES :

- Design, develop, test, and deploy scalable, reliable, and secure backend applications and platforms.

- Lead technical design discussions and contribute to architecture decisions across backend systems.

- Build clean, maintainable, and efficient code following engineering best practices.

- Design and implement APIs, asynchronous workflows, and microservices that are resilient, observable, and easy to scale.

- Build and maintain backend systems for RAG use cases, including ingestion, chunking, embeddings, indexing, retrieval, reranking, and response orchestration.

- Develop agentic AI workflows with tool calling, multi-step execution, state management, retries, fallbacks, and guardrails.

- Collaborate with Product Managers, QA teams, data teams, and other stakeholders to define and deliver product requirements.

- Review code, provide constructive feedback, and mentor junior developers.

- Troubleshoot complex technical issues and implement effective solutions.

- Optimize application performance, scalability, reliability, and cost efficiency.

- Maintain technical documentation for systems, workflows, and architecture decisions.

REQUIREMENTS :

- 3 to 6 years of experience in server-side application development.

- Strong hands-on experience with Java, Spring Boot, Microservices, Redis, MySQL, Kafka, Elasticsearch/OpenSearch, and AWS.

- Demonstrated experience in building and scaling production-grade backend systems.

- Strong knowledge of REST APIs, distributed systems, backend architecture, and event-driven systems.

- Hands-on experience building or integrating LLM-powered applications, RAG pipelines, or agentic AI workflows.

- Good understanding of RAG concepts including chunking, embeddings, vector search, hybrid retrieval, metadata filtering, reranking, and grounding.

- Experience with tool calling patterns and backend orchestration for workflows involving external APIs and multi-step execution.

- Ability to evaluate tradeoffs across accuracy, latency, reliability, observability, and cost for AI-powered systems.

- Strong foundation in data structures, algorithms, and system design.

- Deep understanding of software design and architecture.

- Excellent analytical, organizational, and problem-solving skills.

- Strong verbal and written communication skills.

PREFERRED :

- Experience with vector databases or retrieval infrastructure.

- Familiarity with frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent.

- Experience evaluating and monitoring RAG and agentic systems in production.

- Ability to independently drive ambiguous backend and AI problem statements to production.

WHY JOIN US ?

- Work in a fast-paced, high-growth environment.

- Build real-world AI-native backend systems, not just prototypes.

- Collaborate with a strong team solving product and platform problems at scale.

- Get the opportunity to lead and innovate in a tech-first organization.

- Competitive compensation and exciting growth opportunities.