Data Scientist

Data Scientist (Remote within the UK)
 
About the Role:
 
We are seeking a highly skilled and innovative Data Scientist with hands-on experience in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), RAG Graph, and Knowledge-Augmented Generation (KAG). You will be working on cutting-edge AI systems that blend open-source technologies and enterprise-scale architecture to solve complex information retrieval and natural language understanding problems.
 
Key Responsibilities:

• Design, develop, and deploy RAG pipelines using LLMs (e.g., OpenAI, LLaMA, Mistral, Claude).
• Architect and implement RAG Graph systems integrating vector databases, knowledge graphs, and structured data sources.
• Lead the design and development of Knowledge-Augmented Generation (KAG) systems for enhanced context-aware reasoning.
• Contribute to both open-source initiatives and proprietary enterprise-grade solutions.
• Build robust data ingestion, preprocessing, and embedding pipelines for unstructured and semi-structured data.
• Evaluate and fine-tune models for performance, relevance, hallucination reduction, and cost-efficiency.
• Work collaboratively with ML engineers, data engineers, and software developers to integrate LLM-based components into products.
• Stay updated with the latest advancements in AI/LLMs and translate research into applied solutions.

Required Skills & Experience:

• Strong background in machine learning, NLP, and deep learning.
• Hands-on experience with LLM frameworks and APIs (OpenAI, HuggingFace Transformers, LangChain, LlamaIndex).
• Experience building RAG pipelines with tools such as FAISS, Weaviate, Qdrant, or Pinecone.
• Solid knowledge of graph databases (Neo4j, TigerGraph) and knowledge graph construction.
• Proficiency in Python, with deep experience in data science and ML libraries (PyTorch, TensorFlow, Scikit-learn).
• Familiarity with MLOps, containerization (Docker), and cloud platforms (AWS, Azure, GCP).
• Strong problem-solving skills and the ability to work independently and as part of a collaborative team.

Preferred Qualifications:

• Experience with KAG systems, semantic search, or context-aware generation techniques.
• Contributions to open-source AI projects or community involvement.
• Academic background (MSc/PhD) in Computer Science, Data Science, Mathematics, or related fields.
• Familiarity with enterprise security, compliance, and data governance considerations for AI applications.

 
Why Join Us?

• Be part of a dynamic, forward-thinking AI team building next-gen enterprise AI capabilities.
• Work with the latest in open-source and commercial AI technologies.
• Flexible remote or hybrid work model (UK-based).
• Opportunity to shape product direction and AI architecture in real-world enterprise scenarios.