Senior AI Engineers

Candidate Requirements
Seniority Level
Senior
Professional Experience
6+ years

Technology Stack
- Graph Databases: Familiarity with graph databases like Neo4j, TypeDB, NebulaGraph, and ArangoDB indicates experience with storing and managing complex, entity-based relationships essential for GraphRAG operations

- Knowledge Graph Construction: Skills with knowledge graph frameworks and semantic data modeling are key, so look for experience with RDF (Resource Description Framework), SPARQL (for querying RDF), OWL (Web Ontology Language), and tools like Protégé. These are crucial for building structured, queryable graphs that enhance LLM contextual understanding.

- RAG Libraries and LLM Orchestration: Experience with LangChain, Haystack, or RAGFlow—tools that provide RAG pipelines and manage knowledge augmentation for LLMs—is valuable. These libraries are often used to implement RAG techniques in LLM applications, integrating retrieval systems directly with models

- Large Language Model Platforms: Familiarity with LLM frameworks like OpenAI’s API, Hugging Face Transformers, LLamaIndex, and Azure Cognitive Services suggests experience with model orchestration and deployment, especially for knowledge-augmented applications.

- Python and Graph Query Languages: Proficiency in Python is essential, as it’s the language of choice for building RAG pipelines and integrating with most ML and NLP frameworks. Also, knowledge of Cypher (for Neo4j), Gremlin (Apache TinkerPop), and GQL (Graph Query Language) supports direct interaction with graph databases.

- Causal Inference Tools: Familiarity with causal reasoning tools like DoWhy, EconML, or CausalNex is beneficial, as these enable causal inference within graph structures, supporting the explanatory capabilities that often accompany GraphRAG setups.

Project Responsibilities and Team
Responsibilities on the Project
Experienced Senior AI Engineer with deep expertise in Large Language Models (LLMs), GraphRAG (Graph + Retrieval-Augmented Generation), and Causal AI is needed to transform the client’s current LLM+Causal AI prototype into a robust, production-ready solution. The ideal candidate has strong proficiency in Python, a solid grasp of semantics and graph database structures, and a passion for building AI-driven products that leverage causal reasoning and knowledge graphs.

Project Team
Will work with a team of 3-4 other senior engineers



Longterm (6-12 months)




👍English: C1

🌍 Location: Poland is preferred (Europe is possible)




📩 Ready to Join?
We look forward to receiving your application and welcoming you to our team!