and leveraging both structured and unstructured data sources. Experimenting with the integration and fine-tuning of models with Vector databases and embeddings to support semantic search, RAG (retrieval-augmentedgeneration), and domain-specific applications. Working within a Data Mesh architecture, collaborating across domains to ensure scalable, interoperable data products; containerising solutions with Docker and More ❯
systems (retrieval, memory modeling, task orchestration) Integrate structured and unstructured knowledge from multiple modalities (text, image, video) into agent workflows Develop solutions coupling retrieval (KGs, RAG, databases) with planning, reasoning, and execution logic Collaborate with engineering teams on LLM platforms, search infrastructure, and agent systems Translate research into production-ready applications across AI development tools, QA … skills Experience working across research and applied development in a collaborative environment Keywords: Knowledge Graphs/LLMs/Semantic Search/Knowledge Reasoning/NLP/Agent Systems/RAG/OWL/SPARQL/Transformers/Deep Learning/AI Assistants/QA Systems/Pytorch/TensorFlow/Graph Reasoning/Multi-Modal AI/Knowledge Engineering/ More ❯
and task orchestration. Drive the development of memory capabilities for intelligent agents, integrating structured and unstructured knowledge from multiple modalities. Architect solutions that deeply couple retrieval systems (RAG, KGs, databases) with agent planning, reasoning, and execution workflows. Work closely with LLM platforms, search infrastructure, and knowledge graph systems to build collaborative end-to-end agent solutions. Translate cutting More ❯
feature work* • Design and ship REST or GraphQL endpoints. • Build multi-tenant data models and role-based workflows. • Trigger emails and webhooks for status changes. *AI/Retrieval-AugmentedGeneration* • Wire existing prompts to an LLM API (OpenAI-compatible today, private model later). • Store embeddings in a vector store and perform RAG look More ❯
