AI engineer for LLM systems

RITS; Warszawa; Hybrid; PLN 141,000 - 234,000; Full time

Job summary

RITS Group ищет опытного Senior AI Engineer для проекта клиента. Вы будете разрабатывать системы на основе больших языковых моделей (LLMs), работать с неструктурированными данными и обеспечивать взаимодействие с данными через естественный язык.

Задачи включают построение конвейеров обработки данных, OCR/ASR, генерацию эмбеддингов, интеграцию сервисов и API для AI-решений, тестирование и улучшение надёжности. Это гибридная роль с B2B и стартом ASAP.

Qualifications

• Опыт разработки решений на основе LLM.
• Опыт работы с REST API.
• Знание Java и/или Python.
• Опыт работы с BigQuery.
• Глубокое понимание лучших практик разработки ПО.

Responsibilities

• Разработка систем, позволяющих задавать вопросы к данным на естественном языке и генерировать SQL.
• Поддержка платформы обработки и хранения неконструктивных данных (документы, изображения, аудио).
• Проектирование конвейеров обработки данных, включая OCR, ASR и генерацию эмбеддингов.
• Создание сервисов для категоризации данных и интеграции компонентов.
• Оценка решений на LLM – тестирование качества и повышение надежности.
• Разработка сервисов и API для AI-решений.
• Соблюдение практик разработки, тестирования и сопровождение.

Skills

Java

Python

LLM frameworks

REST APIs

Testing

Tools

LangChain4j

Google ADK

Pydantic AI

Spring AI

BigQuery

Job description

Описание: RITS Group is an IT company that offers the highest quality software development services to both the Polish and international markets. We are proud to be among the fastest-growing technology companies. Our priorities are the quality and innovation of the solutions we deliver, and our organizational culture is based on trust, collaboration and continuous improvement. We are looking for an experienced Senior AI Engineer to join a project delivered for our client. You will develop modern solutions based on large language models (LLMs), work with unstructured data and co-create systems that enable users to interact with data using natural language.

Задачи

• Building a system that enables users to ask questions about data in natural language, interpret user intent, generate SQL queries and execute them securely.
• Supporting a platform for processing, storing and sharing unstructured data such as documents, images and audio recordings.
• Designing data ingestion and processing pipelines, including content extraction, OCR, ASR and embedding generation.
• Creating services responsible for data categorization, ontology management and integration of different system components.
• Evaluating LLM solutions—testing response quality, diagnosing errors, and improving system reliability and security.
• Designing and developing services and APIs that support AI solutions.
• Applying good programming practices, testing and maintaining the solutions being developed.

Требования

• Very good knowledge of Java and/or Python.
• Practical experience creating solutions that use LLMs.
• Knowledge of at least one framework, such as LangChain4j, Google ADK, Pydantic AI or Spring AI.
• Knowledge of Google BigQuery, including SQL, data modeling, and query cost and performance optimization.
• Experience creating services and integrations using REST APIs.
• Ability to test, evaluate and diagnose LLM-based systems.
• Knowledge of good practices for creating, deploying and maintaining software.
• You do not need to know all the technologies listed.
• The most important things are solid software engineering fundamentals, practical experience with LLMs, and willingness to develop skills in Chat with Data and unstructured data processing.
• Будет плюсом: Experience with NL2SQL, Conversational Analytics or BI-as-Chat solutions; Knowledge of RAG, embeddings, chunking and reranking; Experience processing documents, images and audio recordings, including OCR, text extraction and transcription; Knowledge of GenAI system evaluation methods, offline and online testing, and prompt versioning; Experience with semantic layers, metrics layers, caching and data pre-aggregation; Knowledge of MCP and agentic architectures; Experience with vector databases, such as Qdrant, Pinecone, Weaviate or Milvus; Knowledge of graph databases, such as Neo4j, and the GraphRAG approach; Knowledge of FastAPI, Kubernetes, Cloud Run and Pub/Sub; Knowledge of Rust; Experience in regulated environments, particularly in auditing, data classification, access control and protection of sensitive data

Условия

• Cooperation arrangement: B2B contract.
• Rate: up to PLN 170.20 net + VAT/hour.
• Cooperation model: hybrid, according to project requirements.
• Start: ASAP.