We are looking for a Backend AI Developer:
This role involves building an AI-powered tool designed for enterprise clients. It sits at the intersection of strong backend Java engineering and applied AI, focusing on designing and developing intelligent agents using Java and Spring-based technologies.
Responsibilities:
- Design, build, and deploy AI agents and agentic workflows using Java and Spring Boot.
- Develop production-quality APIs and backend services using Java 21 and Spring Boot 3.x.
- Implement agent capabilities including tool/function calling, memory and context management, planning, orchestration, retries, guardrails, validation, and multi-step workflows.
- Use Spring AI or LangChain4j to integrate LLMs and orchestrate agent workflows within Spring applications.
- Design effective LLM prompts using templates, roles, constraints, and structured outputs.
- Build and maintain LLM evaluations to measure agent quality, reliability, and performance.
- Implement LLM observability and monitoring, including tracing, latency, token usage, cost, and failure analysis.
- Apply RAG techniques, including chunking, embeddings, vector databases, and retrieval optimization.
- Use AI coding tools such as GitHub Copilot or Amazon Q as part of the daily software development workflow.
- Collaborate with engineers and stakeholders to prototype, test, and continuously improve AI capabilities.
- Write clean, maintainable, well-tested Java code while incorporating AI capabilities into production applications.
Requirements:
- Strong professional experience with Java, including modern Java versions such as Java 21.
- Strong experience with Spring Boot 3.x, including Spring Web, Spring Data, and Spring Security.
- Proven ability to build and support production APIs and backend services.
- Strong understanding of software engineering fundamentals, testing, debugging, and API design.
Required Skills:
- Hands-on experience building AI agents or agentic applications.
- Experience with Spring AI, LangChain4j, or a comparable agent/LLM orchestration framework.
- Understanding of agent architecture, including tool calling, memory, planning, orchestration, retries, and guardrails.
- Hands-on experience with LLM prompt design and prompt engineering.
- Experience designing or developing LLM evaluations.
- Understanding of RAG fundamentals, including embeddings, chunking, vector databases, and retrieval tuning.
- Experience with at least one LLM observability/monitoring platform, such as Langfuse, Arize, Weights & Biases, or Datadog.
- Daily hands-on experience using AI coding assistants, such as GitHub Copilot or Amazon Q.
- Comfortable incorporating AI into development, testing, debugging, refactoring, and code-generation workflows.
Preferred Skills:
- Experience optimizing LLM applications for performance and cost, including caching, batching, model routing, and prompt/token optimization.
- Experience evaluating and selecting AI models based on quality, latency, cost, and risk.
- Experience deploying AI services to AWS, Azure, or GCP.
- Experience with CLI-based coding assistants such as GitHub Copilot CLI or Claude Code.
- Experience with spec-to-code development, AI-generated testing, or automated refactoring.
- Experience with MCP (Model Context Protocol) or OpenAPI-based tool schemas.
- Experience integrating AI agents with enterprise APIs, databases, and external tools.