Software Developer (AI)

We are looking for an experienced Java Developer with strong backend engineering skills and proven experience in AI-related technologies and frameworks. The ideal candidate has at least 3 years of professional Java experience, writes clean, maintainable code, and is comfortable working on scalable distributed systems. 

A strong interest in data, AI-driven applications, vector search, and modern LLM tooling is highly valued. 

We are looking for a team player who thrives in collaborative environments, enjoys knowledge sharing, and contributes actively to technical discussions and solution design. 

Key Responsibilities 

• Designing and implementing AI agents with reasoning pipelines (e.g. multi-step workflows, tool usage, RAG-based decision making) 

• Integrating AI capabilities such as LLM-powered services, semantic search, and intelligent automation 

• Contributing to scalable architectures for data- and event-driven systems 

• Improving, refactoring, and maintaining existing codebases 

• Designing tasks in collaboration with the Team Lead and Product Owner 

• Participating in code reviews, architecture discussions, and knowledge sharing 

• Contribute to the design of scalable architectures for data-heavy and AI-driven services 

• Collaborate closely with the Team Lead and Product Owner to design tasks and shape technical solutions 

• Participate in code reviews, architecture discussions, and knowledge-sharing sessions 

Required Skills & Technology:

• English min B2 + Polish or C1

• Experience - minimum 3 years

Java:

• Spring Boot

• Docker

AI-related:

• Spring AI

• Experience integrating LLMs into applications (OpenAI API, Anthropic, local inference, etc.)

• Understanding of vector databases (Milvus, Pinecone, Qdrant, Elasticsearch vector search, or similar)

• AWS Bedrock

• LangChain4j

• Knowledge of embeddings, prompt engineering basics, and retrieval-augmented generation (RAG)

• Understanding Model Context Protocol

Nice to Have:

• Redis

• Mongo DB

AI-related:

• Experience with AI/ML frameworks or orchestration libraries (LangChain4j, Spring AI, Embabel, Haystack, etc.)

• Familiarity with LLM model lifecycle: prompt design, evaluation, latency considerations, cost/performance trade-offs

• Experience with Ollama / vLLM

• Experience with streaming architectures for AI pipelines (i.e. Kafka Streams)

• Experience with document processing, OCR, or semantic search
  

Perks in the office:

• Modern office full of coffee, snacks, and beverages

• Bike parking, great location of the office

Benefits:

• Training budget for self-development, courses, conferences, and more

• A smart benefits platform that lets you easily manage subscriptions and purchases — including sports and lunch cards.

• Flat structure and small teams

• International project

• Team Events

• Private healthcare, Life & group insurance

• We celebrate birthdays and other important employee events
  

Recruitment process:

1. Screening (15-30 min) -> We want to get to know you and answer your questions - it is up to you how much time we need.

2. Recruiting Task - Show your skills :) We will send you a task, you decide how much time you need to complete it.

3. Video call (1h/2h)-> Let's talk about your coding style, exchange experiences, and get to know each other a little better. 

Data Sharing - the best way to better data.

We are passionate about new technologies and we constantly improve our stack. There is always enough room to learn the ropes as we provide internal and external training and education. We are looking for a person who loves high-quality of code and who is interested in big sets of data.

90% of the world's data has been produced in just the last two years. Our mission is to help companies with our innovative Data Quality Services. CDQ is the first company in the market to leverage Data Sharing as the best way to better data. Our customers share data quality rules, enrich their data from publicly shared sources, exchange hand-validated data records, and alert each other of data fraud. The result of collaborative master data management: Higher efficiency, shared efforts, better quality, less risks.

With our cloud-based software platform, CDQ can provide Data Quality as a Service – customers' master data is monitored and updated continuously, using our Data Quality Tools software or fully integrated with their ERP or CRM systems.