Full Stack Engineer

Senior Full Stack Engineer – Java, Spring Boot & AI

About Code17

Code17 provides technology consulting and professional services across data engineering, cloud, full-stack development, and agentic AI. We help enterprises build modern applications and implement AI solutions that improve business operations.

Role Overview

We are seeking a Senior Full Stack Engineer with strong Java and Spring Boot expertise and hands‑on experience building AI-powered applications. The ideal candidate can develop applications across the frontend and backend while integrating large language models, Retrieval-Augmented Generation (RAG), and Model Context Protocol (MCP).

This role requires practical software engineering experience, including taking AI capabilities from prototypes into secure, reliable production applications.

Key Responsibilities

• Design, develop, and maintain applications using Java, Spring Boot, and React or Angular.
• Build REST APIs, microservices, and integrations with enterprise systems.
• Develop RAG pipelines covering document ingestion, parsing, chunking, embeddings, vector retrieval, reranking, and grounded response generation.
• Integrate LLMs through cloud AI platforms or model provider APIs.
• Build and integrate MCP servers and clients to connect AI applications with enterprise tools, APIs, and data sources.
• Implement AI workflows using tool calling, structured outputs, and orchestration frameworks.
• Apply authentication, authorization, and data access controls across application and AI workflows.
• Evaluate AI response quality, retrieval accuracy, latency, and cost; troubleshoot failures and improve performance.
• Write automated tests, participate in code reviews, and support CI/CD and production releases.
• Collaborate with product owners, architects, and business stakeholders to translate requirements into working solutions.

Required Qualifications

• 5+ years of professional software development experience, with strong hands‑on Java and Spring Boot expertise.
• Strong understanding of REST API design, microservices, object‑oriented programming, and design patterns.
• Experience with relational databases such as PostgreSQL or MySQL, including SQL development and performance tuning.
• Hands‑on experience developing LLM-powered applications beyond basic chatbot integrations.
• Practical experience implementing RAG, including embeddings, vector databases, retrieval strategies, and metadata filtering.
• Experience implementing or integrating MCP servers or clients, with an understanding of tool discovery, invocation, and access controls.
• Experience with prompt design, tool/function calling, structured outputs, and managing model context.
• Familiarity with vector search platforms such as Qdrant, pgvector, Pinecone, OpenSearch, or equivalent.
• Experience with Git, automated testing, Docker, and CI/CD pipelines.
• Strong problem‑solving, communication, and collaboration skills.

Preferred Qualifications

• Experience with Spring AI, LangChain4j, or comparable Java AI frameworks.
• Python experience for AI services, data processing, or orchestration.
• Experience with Amazon Bedrock, Azure OpenAI, Google Vertex AI, or comparable AI platforms.
• Familiarity with agent frameworks such as LangGraph, Semantic Kernel, or AWS Strands.
• Experience with hybrid search, reranking, and retrieval evaluation.
• Understanding of prompt injection risks, sensitive data protection, and safe execution of AI‑invoked tools.
• Experience with Kubernetes, messaging platforms such as Kafka, and cloud deployment.
• Experience implementing human approval steps, retries, audit logs, and observability for AI workflows.

What Success Looks Like

• Deliver maintainable full-stack features with reliable backend services and intuitive user interfaces.
• Build AI capabilities that retrieve relevant information and produce grounded, useful responses.
• Connect AI workflows securely to enterprise systems through well‑designed APIs and MCP integrations.
• Demonstrate measurable improvements in application reliability, AI quality, response time, and operating cost.