Data Engineer (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Data Engineer (AI): Building and maintaining automated data pipelines for an AI-assisted legacy-code documentation platform with an accent on AST processing, knowledge graphs, vector search, and structured data transformation. Focus on integrating Neo4j, Qdrant, Tree-sitter, and self-hosted LLMs while validating data quality, pipeline consistency, and large-scale processing performance.
Location: Remote within Poland
Company
is a custom product engineering company supporting multinational organizations and scaling startups through software development, consulting, analytics, and product engineering.
What you will do
- Develop, test, and maintain production data pipelines processing AST outputs, knowledge graphs, vector embeddings, and metadata.
- Ingest, normalize, and update code dependency graphs in Neo4j and vector indexes in Qdrant.
- Transform raw source-code structures into structured Markdown assets and standardized JSON/RAG inputs.
- Monitor pipeline throughput, troubleshoot batch-processing errors, and maintain consistent data states.
- Collaborate with Senior Data Engineers and AI/ML Engineers to improve retrieval speed and pipeline efficiency.
Requirements
- 3+ years of commercial experience building and maintaining production data pipelines.
- Solid proficiency in Python, SQL, and data manipulation frameworks.
- Hands-on experience with graph databases, vector search engines, or static code parsing frameworks such as Neo4j, Qdrant, and Tree-sitter.
- Proficiency with Git, Docker, unit and integration testing, and CI/CD workflows.
- Strong analytical skills focused on data accuracy, schema consistency, and output validation.
- Professional English proficiency at B2+/C1 level required.
Culture & Benefits
- Full remote working possibilities within Poland.
- Access to meetups, conferences, workshops, Udemy, language courses, and company-paid certifications.
- Opportunities to work on large-scale, globally impactful projects and move between internal domains.
- Company-paid premium medical coverage through Luxmed.
- MyBenefit cafeteria platform with customizable perks.
- Collaborative One Team culture with delivery centers in Wrocław and Gdańsk.
Hiring process
- Submit an application to begin the recruitment process.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →