Knowledge Engineer, Fully Remote, £80,000 - £100,000 per annum

My client, a leading AI solutions company are seeking a Mid-Senior Python Backend Engineer with a passion for knowledge graphs and semantic web technologies. In this role, you will own the full Back End development for an RDF-intensive platform - designing and optimising systems around triple stores (AWS Neptune), Real Time data processing and validation with SHACL, and advanced query capabilities. You will integrate AI-driven SPARQL generation models (LLMs/NLP) to enable intelligent querying of the knowledge graph. Working in a cross-functional squad of 3-8 team members using a Lean Kanban approach, you'll collaborate closely with product, data scientists, and DevOps to deliver high-quality features in a fast-paced, agile environment.

Key Responsibilities:

Design and Develop Knowledge Graph Backends: Build robust Back End services to manage RDF data in triple stores (AWS Neptune) and vector embeddings in Milvus. Ensure Real Time processing of graph data, including on-the-fly validation with SHACL to maintain data integrity.

SPARQL Query Implementation & AI Integration: Create efficient SPARQL queries and endpoints for data retrieval. Integrate NLP/AI models (eg Hugging Face transformers, OpenAI APIs, LlamaIndex AgentFlow) to translate natural language into SPARQL queries, enabling AI-driven query generation and semantic search.

API & Microservices Development: Develop and maintain RESTful APIs and GraphQL endpoints (using FastAPI or Flask) to expose knowledge graph data and services. Follow microservices architecture best practices to ensure components are modular, scalable, and easy to maintain.

Database & State Management: Manage data storage solutions including PostgreSQL (for application/session state) and caching layers as needed. Use SQLAlchemy or similar ORM for efficient database interactions and maintain data consistency between the relational and graph data stores.

Performance Optimisation & Scalability: Optimise SPARQL queries, data indexing (including vector indices in Milvus), and service architecture for low-latency, Real Time responses. Ensure the system scales to handle growing knowledge graph data and high query volumes.

DevOps and Deployment: Collaborate with DevOps to containerize and deploy services using Docker and Kubernetes. Implement CI/CD pipelines for automated testing and deployment. Monitor services on cloud platforms (AWS/Azure) for reliability, and participate in performance tuning and troubleshooting as needed.

Team Collaboration: Work closely within a small, cross-functional squad (engineers, QA, product, data scientists) to plan and deliver features. Participate in Lean Kanban rituals (eg stand-ups, continuous flow planning) to ensure steady progress. Mentor junior developers when necessary and uphold best practices in code quality, testing, and documentation.

Required Skills and Experience:

Programming Languages: Strong proficiency in Python (Back End development focus). Solid experience writing and optimizing SPARQL queries for RDF data. Knowledge Graph & Semantic Web: Hands-on experience with RDF and triple stores- ideally AWS Neptune or similar graph databases. Familiarity with RDF schemas/ontologies and concepts like triples, graphs, and URIs.

SHACL & Data Validation: Experience using SHACL (Shapes Constraint Language) or similar tools for Real Time data validation in knowledge graphs. Ability to define and enforce data schemas/constraints to ensure data quality. Vector Stores: Practical knowledge of vector databases such as Milvus (or alternatives like FAISS, Pinecone) for storing and querying embeddings. Understanding of how to integrate vector similarity search with knowledge graph data for enhanced query results.

Frameworks & Libraries: Proficiency with libraries like RDFLib for handling RDF data in Python and PySHACL for running SHACL validations. Experience with SQLAlchemy (or other ORMs) for PostgreSQL. Familiarity with LlamaIndex (AgentFlow) or similar frameworks for connecting language models to data sources.

API Development: Proven experience building Back End RESTful APIs (FastAPI, Flask or similar) and/or GraphQL APIs. Knowledge of designing API contracts, versioning, and authentication/authorization mechanisms.

Microservices & Architecture: Understanding of microservices architecture and patterns. Ability to design decoupled services and work with message queues or event streams if needed for Real Time processing.

AI/ML Integration: Experience integrating NLP/LLM models (Hugging Face transformers, OpenAI, etc.) into applications. Specifically, comfort with leveraging AI to generate or optimize queries (eg, natural language to SPARQL translation) and working with frameworks like LlamaIndex to bridge AI and the knowledge graph.

Databases: Strong SQL skills and experience with PostgreSQL (for transactional data or session state). Ability to write efficient queries and design relational schemas that complement the knowledge graph. Basic understanding of how relational data can link to graph data.

Cloud & DevOps: Experience deploying applications on AWS or Azure. Proficiency with Docker for containerization and Kubernetes for orchestration. Experience setting up CI/CD pipelines (GitHub Actions, Jenkins, or similar) to automate testing and deployment. Familiarity with cloud services (AWS Neptune, S3, networking, monitoring tools etc.) is a plus.

Agile Collaboration: Comfortable working in an Agile/Lean Kanban software development process. Strong collaboration and communication skills to function effectively in a remote or hybrid work environment. Ability to take ownership of tasks and drive them to completion with minimal supervision, while also engaging with the team for feedback and knowledge sharing.