Descripción de la oferta
We are seeking an experienced Knowledge Engineer to design, implement, and scale state-of-the-art AI systems that combine large language models, advanced retrieval techniques, cognitive memory architectures, and data fusion. You will orchestrate robust data pipelines, architect scalable training data solutions, and build the foundational knowledge bases that power next-generation AI agents. Responsibilities Design and optimise RAG workflows integrating local LLMs with retrieval mechanisms including vector search, Elasticsearch, FAISS, and Weaviate. Build and maintain scalable data pipelines for ingesting, transforming, indexing, and retrieving structured and unstructured data. Design services and tool specifications that LLMs and agents can leverage to orchestrate workflows. Manage training data operations including curation, versioning, and lineage tracking for LLM fine-tuning. Develop ontologies, knowledge graphs, and semantic data models for improved retrieval and reasoning. Design cognitive memory systems for AI agents enabling persistent knowledge retention across interactions. Required Skills Bachelor's or Master's degree in related field. Proven experience designing and scaling data pipelines for LLMs. Strong background in information retrieval, vector search, and RAG frameworks. Proficiency in Python and ML libraries including TensorFlow and PyTorch. Experience with ontologies, knowledge graphs, and semantic technologies such as RDF, OWL, and SPARQL. Familiarity with distributed data processing tools including Spark, Airflow, and Kubeflow. Nice to Haves Experience with LLM fine-tuning and prompt engineering. Familiarity with data-centric AI principles. Experience with cloud platforms and scalable storage. Background in cognitive memory architectures or AI agent design. #J-18808-Ljbffr
