Job details:

• Fully Remote,with possible occasional in person team sessions (i.e. 1x quarter) likely to take place in Prague.
• Full-time
• 12 months (extensions possible)
• Working Hours: Must be able to overlap with US hours (2-6pm CET)

Role Summary:

We are looking for a Senior Data Engineer to build scalable, production-grade data and AI-enabled systems using Python, knowledge graphs, Cosmos DB, Gremlin API, and GraphRAG. The role requires strong hands-on engineering skills, an ownership mindset, and the ability to contribute to architecture, implementation, and delivery. Senior hands-on engineer who can work independently, make technical decisions, and deliver high-quality data, graph, backend, and AI-enabled solutions.

Key Responsibilities:

• Design and develop scalable data pipelines, backend services, and APIs using Python.
• Build and maintain knowledge graph solutions, including graph data modeling, relationship mapping, and graph traversal logic.
• Work with Azure Cosmos DB, Gremlin API, and graph databases such as Neo4j.
• Design and implement GraphRAG solutions combining knowledge graphs, vector search, metadata, and LLM-based retrieval.
• Contribute to technical design, code quality, testing, performance optimization, and production support.
• Collaborate with product, engineering, data, and AI teams to deliver reliable software solutions.
• Support full-stack development where needed using React and Next.js..

Requirements:

• Strong commercial experience with Python backend or data engineering development.
• Hands-on experience with knowledge graphs, graph data modeling, and graph-based applications.
• Experience with Cosmos DB, Gremlin API, and/or Neo4j.
• Good understanding of GraphRAG, RAG pipelines, LLMs, embeddings, and AI-enabled retrieval systems.

GenAI / AI engineering experience, especially with:

• LangChain, LangGraph
• LLMs and RAG
• MCP server/client integration and hosting
• Agent memory management
• AI engineering and spec-driven development
• Experience with data pipelines, API design, scalable architecture, and software engineering best practices.
• Comfortable working in cloud-based environments and modern delivery workflows.
• Working knowledge of React and Next.js is preferred
• Exposure to AI/ML concepts or LLM integrations

Nice to have:

• Experience with Databricks or similar data platforms.
• Experience with vector databases, Azure AI Search, or semantic search platforms.
• Docker, Kubernetes, CI/CD, or cloud platform experience

SNI sp. z o.o. will process personal data for the purpose of the recruitment process in accordance with Data Privacy Policy. The data may also be stored and processed for future recruitment purposes, in accordance with the given consent.