PNNL

Software Engineer II on the Research AI Workflows Team at PNNL, specializing in scaling AI applications across HPC and cloud environments.

Experience

• Efficient distributed training of vision-language models on multi-node, multi-GPU clusters
• Deploying scalable cloud infrastructure with AWS 
• LLM application development using LlamaIndex and LangGraph
• Containerization and CI/CD automation with Docker and GitLab

Key Projects

• PermitAI: Custom end-to-end Agentic RAG pipeline (ChatNEPA)
• Distributed LLM training on on-prem HPC systems
• LLM tutorials for HPC documentation
• Multi-agent systems and sandbox environments for LLM testing

• Master of Science in Artificial Intelligence, San Jose State University
• Bachelor of Science in Computer Science, California State University

• Lilienthal, Derek B., "Synthetic Data Generation for Accurate, Fair, and Private Recommender Systems" (2024). Master's Theses. 5515. DOI: https://doi.org/10.31979/etd.ggt3-adtq
• D. Lilienthal, P. Mello, M. Eirinaki and S. Tiomkin, "Multi-Resolution Diffusion for Privacy-Sensitive Recommender Systems," in IEEE Access, vol. 12, pp. 58275-58287, 2024, doi: 10.1109/ACCESS.2024.3388299.
• M. Chowdhary, D. Lilienthal, S. S. Saha and K. C. Palle, "AutoML for On-Sensor Tiny Machine Learning," in IEEE Sensors Letters, vol. 7, no. 11, pp. 1-4, Nov. 2023, Art no. 6008504, doi: 10.1109/LSENS.2023.3327914.
• Zeng, Q. R, Lilienthal, D., Iordan, M., & Piazza, E. A. (2022). Using a Language Transformer Model to Capture Creativity in Improvised Narratives. Proceedings of the Annual Meeting of the Cognitive Science Society, 44.
• D. Lilienthal, “Analysis of foreign media influence on the south pacific environment,” SIAM Undergraduate Research Online, vol. 14, 2021. doi:10.1137/21s1403242