Ai & Knowledge Graph Engineer

About us

At Umanitek, we work at the frontier of neuro-symbolic AI to build systems that protect humans from deepfakes and impersonation. Our core product, the Umanitek Guardian pipeline and agent network, grounds intelligence in RDF knowledge graphs to provide robust threat detection. We are dedicated to building hybrid reasoning capabilities that combine SPARQL-driven graph logic, risk scoring, entity resolution, embedding similarity, and media analysis into a single, coherent system to defend against modern digital threats.

Responsibilities

• Develop and optimize hybrid reasoning systems combining Knowledge Graphs, LLMs, embedding search, and symbolic reasoning.
• Build and evolve the Guardian stack (RDF, SPARQL, provenance modeling, schema/ontology design) for neuro-symbolic reasoning.
• Build and test data collection tools enabling Guardian's AI analysis system to securely process data from multiple data sources at scale.
• Measure and improve risk scoring, graph reasoning quality, and end-to-end detection performance.
• Design efficient SPARQL queries and graph patterns for threat discovery, author reputation, and coordinated attack detection.
• Integrate media-analysis capabilities (image/video processing, OCR, similarity signals) for harmful content discovery and tracking.
• Integrate perceptual hashing and similarity search algorithms for image/video discovery.
• Ensure scalability, data quality, and operational reliability of the Guardian knowledge base and orchestration pipeline.

Qualifications

• The candidate has held the job title AI & Knowledge Graph Engineer or its equivalent.
• The candidate must have experience in Knowledge Graphs and Multi-Agent Orchestration, with strong AI capabilities directly related to these domains. General machine learning expertise will be considered secondary unless directly applicable to KG enrichment or multi-agent systems.
• The candidate must have deep technical expertise with knowledge graphs, specifically focusing on RDF, SPARQL, and advanced reasoning approaches. Experience with graph databases like Blazegraph is highly valued.
• The candidate should have experience with artificial intelligence (AI) and large language models (LLMs), embeddings, or reasoning systems, with a strong emphasis on their application within knowledge graph contexts or multi-agent orchestration. Data science and general machine learning expertise will be considered secondary unless directly applicable to KG enrichment or multi-agent systems.
• The candidate must be comfortable navigating Python's async, typing, and multithreading ecosystem including FastAPI, pytest, and pandas.
• The candidate should have knowledge of graph algorithms such as PageRank, community detection, entity resolution, and similarity search.
• The candidate needs proven experience in building and optimizing knowledge graph-centric or multi-agent orchestration data pipelines and ETL processes, with a focus on integrating diverse knowledge representation and reasoning technologies (e.g., Python, GraphDB, APIs & SDKs). General production pipeline experience without a KG or multi-agent focus will be de-emphasized.
• The candidate should be proficient in the specified tech stack and tools, with a strong emphasis on those directly supporting knowledge graph applications and multi-agent orchestration, including RDFLib, GraphDB, and SPARQL query optimization tools. General machine learning tools should be considered secondary unless directly applicable to KG enrichment or multi-agent systems.
• The candidate must be located fully remote in Europe.
• The candidate should have a Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or a related field.
• The candidate should have experience in the cybersecurity or threat-detection industry.