About the project: We are developing a platform with generative AI capabilities integrated into its core. We need a strong Middle/Senior backend developer who not only writes Java but also deeply understands the mechanics of LLMs, can build RAG pipelines, and design complex agents.
Tasks:
- Design and develop microservice architecture on Java 17+ using Spring Boot (MVC, Data JPA, Security).
- Build Retrieval-Augmented Generation (RAG) pipelines: from raw data parsing to embedding indexing.
- Develop and maintain Qdrant vector databases: design sharding schemes, configure hybrid search (BM25 + Dense Vectors), and optimize queries to the vector space.
- Create multi-agent systems based on LangChain/LangGraph for business process automation (classification, entity extraction, decision-making).
- Deep prompt engineering: write prompts from scratch for different user cases of a single agent, implement Few-shot, Chain-of-Thought (CoT) techniques, and structured output (JSON mode).
- Debug model semantics: reduce response entropy, manage variability through inference parameters (temperature, top_p, penalties), implement self-healing mechanisms for LLM external provider degradation.
- Optimize PostgreSQL performance: tune complex SQL queries, work with indexes (B-tree, GIN/GIST, trigrams), design transactional isolation.
- Offload computation to a containerized environment: Docker, Kubernetes (Helm), build fault-tolerant CI/CD pipelines in GitLab CI/Jenkins.
Our expectations from the candidate:
- Confident command of Java 17+. Understanding of multithreading (CompletableFuture, Project Loom virtual threads — a plus).
- Expert level proficiency in the Spring stack: deep understanding of bean lifecycle, aspect-oriented programming, fine-tuning DB connection pools and security parameters.
- Experience in designing relational models in PostgreSQL, ability to read EXPLAIN ANALYZE, handle deadlocks, and write efficient migrations (Liquibase/Flyway).
- Practical experience with vector databases (Qdrant) or Weaviate/Pinecone/Milvus. Understanding of similarity metrics (Cosine Similarity, Dot Product, Euclidean Distance).
- Development experience with LangChain and/or LangGraph libraries. Skill in building state graphs (State Machines) and integrating external tools (tool calling).
- Skill in writing effective prompts (Prompt Engineering) and managing LLM behavior without altering model weights.
- Experience with Docker and Kubernetes (writing manifests, Helm charts). Linux shell knowledge at a confident user level.
- Configured CI/CD processes (GitLab CI or Jenkins): Maven/Gradle build, test coverage (JUnit 5, Testcontainers), static code analysis.
