About the Role:
As a Semantic AI Engineer in our Technology Solutions team, you’ll work at the heart of data engineering, semantic technologies, and Generative AI. You won’t just build pipelines; you’ll architect the “brain” behind enterprise AI. You will be responsible for transforming raw data into high-fidelity Knowledge Graphs that power advanced AI patterns like GraphRAG, ensuring that Large Language Models have access to factual, structured context.
Your Main Responsibilities:
- Engineer the Future: Design and build robust data pipelines that convert heterogeneous data sources into unified Knowledge Graphs.
- Tame Data Entropy: Parse, integrate, and harmonize massive datasets from structured and unstructured sources.
- Bridge Graphs and LLMs: Implement and optimize graph-based Retrieval-Augmented Generation (RAG) patterns to enhance AI accuracy and reduce hallucinations.
- Knowledge Extraction: Develop workflows for unstructured data processing, with a specific emphasis on using Entity Extraction and Linking techniques to derive structured information from documents.
- Innovate constantly: Drive adoption of cutting-edge tools and methodologies in semantic data modeling and ontology engineering.
- Collaborate with Purpose: Work directly with clients to solve complex data challenges, translating business needs into technical AI architectures.
As the ideal candidate, you will have:
Must-haves:
- Core Engineering: Programming skills in Python (preferred), Java, or Scala.
- Data Foundations: Strong foundation in data modeling, ETL processes, and exploratory data analysis.
- AI Literacy: A solid conceptual understanding of LLM principles and architectures (e.g., transformers, tokenization, prompting basics).
- Modern AI Patterns: Familiarity with RAG (Retrieval-Augmented Generation) and the role of Vector databases in AI application development.
- NLP Basics: Basic understanding of Knowledge Extraction, specifically identifying and linking entities within text.
- Professional Rigor: Git version control, CI/CD experience.
- Excellent English communication skills
- A passion for continuous learning
Nice-to-haves:
- Semantic Tech: Hands-on experience with schema languages (RDFS/OWL, SHACL, etc.) and SPARQL.
- Semantic Modeling: Experience with ontology / taxonomy engineering.
- Graph Architectures: Hands-on experience with graph databases and GraphRAG implementation.
- NLP Tech: Exposure to NLP libraries (like SpaCy, etc.).
- Industry Standards: Knowledge of standards like CIM, IFC, or IoT/WoT.
What We Offer:
- Impact: Work on projects that shape how enterprises use AI and knowledge graphs
- Growth: Access to cutting-edge training, conferences, and collaboration on innovation projects
- Culture: A friendly and professional international team where more than 65% of colleagues come from across the globe
- Balance: Flexible working hours and benefits that reflect our belief that a healthy work-life balance is a key driver of efficiency
- Perks: All the good stuff – great coffee, healthy snacks, and a workspace designed for collaboration
Graphwise welcomes applicants of all backgrounds regardless of race, ethnicity, sexual orientation, gender expression, age, disability, and other statuses. Our company culture as well as policies enforced by our active Diversity Equity & Inclusion Group work towards ensuring we have an inclusive workplace.