Java Developer (AI / GenAI)

Описание

Responsibilities

• Design and development of a microservice architecture in Java 17+ using Spring Boot (MVC, Data JPA, Security)
• Building Retrieval-Augmented Generation (RAG) pipelines: from raw data parsing to embedding indexing
• Development and support of Qdrant vector databases: designing sharding schemes, configuring hybrid search (BM25 + Dense Vectors) and optimizing queries to the vector space
• Creation of multi-agent systems based on LangChain/LangGraph for business process automation (classification, entity extraction, decision making)
• Deep prompt engineering: writing prompts from scratch for different user cases of one agent, implementing Few-shot, Chain-of-Thought (CoT) techniques and structured output (JSON mode)
• Debugging model semantics: reducing response entropy, controlling variability through inference parameters (temperature, top_p, penalties), implementing self-healing mechanisms when external LLM providers degrade
• Optimization of PostgreSQL performance: tuning complex SQL queries, working with indexes (B-tree, GIN/GIST, trigrams), designing transaction isolation
• Offloading computations to a containerized environment: Docker, Kubernetes (Helm), building fault-tolerant CI/CD pipelines in GitLab CI/Jenkins

Requirements

• Confident Java 17+ proficiency. Understanding of multithreading (CompletableFuture, Project Loom virtual threads is a plus)
• Expert level proficiency in the Spring stack: deep understanding of the 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, deal with deadlocks and write efficient migrations (Liquibase/Flyway)
• Practical experience with vector DBMS (Qdrant) or Weaviate/Pinecone/Milvus. Understanding of similarity metrics (Cosine Similarity, Dot Product, Euclidean Distance)
• Experience developing with LangChain and/or LangGraph libraries. Skill in building state machines and integrating external tools (tool calling)
• Skill in writing effective prompts (Prompt Engineering) and controlling LLM behavior without changing 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