Senior AI Knowledge Graph Engineer

About the role

You will lead the design and execution of production-grade graph intelligence systems that extract meaning from massive unstructured document collections, enabling enterprise data discovery, classification, and governance. This role owns the full lifecycle of semantic and contextual analysis solutions, from problem definition and data modeling through building and enriching knowledge graphs to deploying ML- and LLM-assisted analytics in production. You will focus on uncovering relationships, patterns, and insights hidden in unstructured data to support AI safety, security, and compliance requirements. You will architect and operate systems that combine knowledge graphs, LLMs, and ML models applied to large-scale unstructured data. You will define and own data pipelines that extract, transform, and enrich entity relationships into robust, production-grade knowledge graphs. You will drive architectural decisions and technical direction for applied AI and graph intelligence solutions across the organization.

Key facts

What you'll do

Design, build, and deploy graph-based AI solutions, combining knowledge graphs, LLMs, and ML models applied to large-scale unstructured data.

Define and own data pipelines that extract, transform, and enrich entity relationships into production-grade knowledge graphs.

Integrate LLMs and ML models into text processing pipelines for classification, embedding generation, document similarity, and semantic analysis.

Design, deploy, and operate graph and vector databases to support retrieval, reasoning, and analytics at scale.

Optimize models and inference pipelines for production constraints including latency, throughput, cost, and infrastructure limitations.

Deploy, monitor, and iterate on ML systems in production environments ensuring reliability, performance, and continuous integration.

Drive architectural decisions and technical direction for applied AI and graph intelligence solutions aligned with business objectives.

Lead collaboration with software engineers, data scientists, and product stakeholders to translate requirements into scalable graph AI implementations.

Establish best practices for semantic analysis, entity resolution, and contextual understanding across diverse document types and domains.

Champion AI safety, security, and compliance considerations throughout the graph lifecycle and model deployment processes.

Contribute to open-source strategies and internal tooling that accelerate graph-based data exploration and insight generation.

Mentor and guide junior engineers by sharing expertise in graph algorithms, ML operations, and production-grade AI system design.

Requirements

You possess proven experience in developing and deploying production knowledge graphs in real business scenarios, demonstrating mastery of graph data models and lifecycle management.

You have a strong hands-on background in developing text-based ML and LLM systems, including prompt context engineering, optimized for production environments with strict reliability and performance demands.

You show strong proficiency in Python, ML / KG frameworks and tools such as Neo4j, NetworkX, Node2Vec, and SentenceTransformers, with the ability to select the right tool for the problem at hand.

You can apply appropriate graph algorithms and design choices for problem solving, including relationship and ontology modeling, feature definition, and supervised versus unsupervised graph analytics.

You demonstrate ability to design clean, modular, and testable ML code in a collaborative engineering environment with strict quality and versioning standards.

You bring experience with MLOps practices, building production-grade Docker images, and developing AI solutions designed for seamless integration into production systems.

You have a track record of collaborating effectively with software engineers, product managers, and business stakeholders across distributed teams and time zones.

You possess strong communication skills and the ability to explain complex ML concepts and system behavior clearly to both technical and non-technical audiences.

You are comfortable working in an in-office environment based in Prague, understanding that this role requires on-site presence in compliance with Everpure policies unless you are on PTO, work travel, or other approved leave.

You hold the right to work in the Czech Republic or are eligible for sponsorship related to this position.

Practical notes

This role is primarily an in-office position based in Prague, Czech Republic, and you will be expected to work from the Prague office in compliance with Everpure policies, unless you are on PTO, work travel, or other approved leave.

No compensation details are provided in the source.

No specific hours, travel frequency, visa details, or application deadlines are stated in the source material.