• Architect, implement, and optimize retrieval-augmented generation (RAG) workflows by integrating local LLMs (e.g., Llama) with retrieval mechanisms (vector search, Elasticsearch, FAISS, Weaviate) • Design, build, and maintain scalable data pipelines for ingesting, transforming, indexing, and retrieving structured and unstructured data from diverse sources • Design, build, and scale addressable services and tools specifications that can be leveraged by LLMs and Agents to orchestrate workflows • Orchestrate and scale training data operations, including data curation, versioning, and lineage tracking for large-scale LLM training and fine-tuning • Develop and maintain ontologies, knowledge graphs, and semantic data models to structure and integrate domain-specific knowledge for improved retrieval and reasoning • Implement and optimize knowledge retrieval strategies (dense/sparse retrieval, ranking algorithms) to maximize system accuracy and relevance • Aggregate disparate knowledge bases and heterogeneous data into a fused approach for access to relevant contextual information • Design cognitive memory systems for AI agents, enabling persistent knowledge retention and contextual awareness across interactions • Collaborate with AI researchers, data scientists, and engineers to align knowledge architecture with business objectives and ensure data quality • Evaluate and integrate new technologies and research advancements in LLMs, RAG, information retrieval, and knowledge representation • Maintain clear and comprehensive documentation of models, pipelines, and workflows.