You are viewing a preview of this job. Log in or register to view more details about this job.

Graduate Fellow — AI & Knowledge Management

 AI & Knowledge Management Position Overview

 Savannah River National Laboratory is seeking a highly motivated graduate fellow to advance our AI-driven knowledge management capabilities. This fellowship is focused on building next-generation systems for intelligent information retrieval, knowledge graph construction, and multi-agent AI workflows that support complex scientific workflows. The successful candidate will bring graduate-level research experience in large language models, retrieval-augmented generation (RAG), or knowledge representation, and a passion for applying these techniques to real-world challenges across scientific and engineering domains.

Responsibilities 

Design and implement knowledge management pipelines using large language models (LLMs), retrieval-augmented generation (RAG), and vector databases to enable intelligent information retrieval across large, multi-modal document corpora • Develop and evaluate multi-agent AI architectures for automated reasoning, summarization, and decision support • Build and maintain knowledge graphs and ontologies to represent complex domain relationships and support semantic search • Collaborate with cross-functional research teams to integrate AI knowledge tools into existing scientific workflows and applications • Author technical documentation, scientific journal articles, and internal reports communicating methods and findings to both technical and non-technical audiences • Participate in code reviews and contribute to a shared, well-maintained research codebase • Monitor and evaluate emerging developments in LLMs, agentic AI, and knowledge management frameworks, and assess their applicability to ongoing projects

Typical Tools & Technologies AI & Knowledge Management • LLM frameworks: LangChain, LlamaIndex, Hugging Face Transformers • Vector databases: ChromaDB, Weaviate, Pinecone, FAISS • Knowledge graph tools: Neo4j, RDFLib, Apache Jena • Embedding and retrieval: OpenAI APIs, sentence-transformers, MTEB benchmarks • Agent orchestration: LangGraph, AutoGen, CrewAI

Core Development • Python libraries: NumPy, pandas, PyTorch, scikit-learn • NLP libraries: spaCy, NLTK, Hugging Face Datasets • Data visualization: Plotly/Dash, Matplotlib • Version control and collaboration: Git, GitHub/GitLab

Qualifications Minimum • Recent graduate (M.S. or Ph.D.) in Computer Science, Data Science, Information Science, or other scientific and engineering disciplines • Strong proficiency in Python, including experience with AI/ML libraries such as PyTorch, Hugging Face Transformers, or LangChain • Foundational understanding of large language models, prompt engineering, and retrieval-augmented generation (RAG) • Experience with or coursework in natural language processing (NLP) or knowledge representation • Ability to clearly document and communicate technical research, including writing reports and presenting findings • Self-directed with strong collaboration and interpersonal skills

Preferred Qualifications • Research experience or publications related to LLMs, knowledge graphs, information retrieval, or multi-agent systems • Hands-on experience building end-to-end RAG pipelines or agentic AI workflows • Familiarity with knowledge graph construction, ontology design, or semantic web technologies (RDF, SPARQL, OWL) • Experience with vector databases or embedding-based search systems • Background in a scientific or national security domain (e.g., environmental science, bioengineering, chemistry) is a plus • Experience working in a research or government laboratory environment

Appointment Details: This is a full-time, 13-month graduate fellowship assignment. The anticipated start date shown in the posting is an example and may be adjusted based on program needs, candidate availability, and onboarding requirements.