Senior AI & Agentic Systems Engineer (Java)

Technologies we use

About the project

This is how we organize our work

This is how we work

Your responsibilities

• Design, develop, and deploy AI-powered applications and agentic systems built on top of robust Java/Spring Boot backends
• Integrate Large Language Models (LLMs) into enterprise-grade applications, ensuring reliability, scalability, and security
• Architect and implement autonomous AI agent workflows capable of reasoning, planning, and executing multi-step tasks
• Design and build RESTful APIs that serve as interfaces between AI components and broader application ecosystems
• Evaluate, select, and integrate AI frameworks and tools (e.g., Spring AI, LangChain4J) to accelerate development of intelligent features
• Collaborate with data scientists, ML engineers, and product teams to translate AI concepts into production-ready solutions
• Develop and refine prompt engineering strategies to optimize LLM outputs for specific business use cases
• Contribute to architectural decisions regarding AI system design, model orchestration, and data pipelines
• Participate in code reviews, ensuring high-quality and maintainable code across AI and backend components
• Stay current with the rapidly evolving AI landscape and advocate for adoption of new tools, patterns, and best practices
• Mentor team members on AI integration patterns and agentic system development approaches

Our requirements

• Minimum of 5 years of professional experience in software development with a strong Java backend focus
• Solid hands-on experience with Spring Boot for building production-grade, enterprise applications
• Proven experience in designing and developing REST APIs following industry best practices
• Demonstrated experience in AI Agents development or LLM integration — including building applications that leverage large language models for reasoning, content generation, or task automation
• Experience with Spring AI or LangChain4J frameworks for building AI-powered Java applications
• Practical knowledge of Prompt Engineering techniques — crafting, testing, and optimizing prompts for consistent and reliable LLM behavior
• Working knowledge of Python for AI/ML scripting, prototyping, or integration with Python-based AI tooling
• Experience with AWS or GCP cloud platforms, particularly services related to AI/ML workloads and scalable application deployment
• Strong understanding of software architecture principles and the ability to design systems that combine traditional backend services with AI components
• Excellent communication skills and the ability to work effectively in cross-functional, international Agile teams
• Proficiency in English (B2+), both written and spoken

Optional

• Experience implementing Retrieval-Augmented Generation (RAG) pipelines for grounding LLM responses in domain-specific knowledge
• Familiarity with Vector Databases (e.g., Pinecone, Weaviate, pgvector, Chroma) for storing and querying embedding representations
• Knowledge of Model Context Protocol (MCP) for standardized communication between AI models and external tools or data sources
• Experience working with Anthropic Claude Code or similar AI-assisted development tools in engineering workflows
• Familiarity with Google Agent Development Kit (ADK) for building and orchestrating multi-agent systems

What we offer

Development opportunities we offer

Benefits