This long-term contract role places a Software Developer within a major utility services firm in Philadelphia to lead on-premises Large Language Model implementations. The position focuses on deploying open-source models like Meta Llama 3 and Mistral using Python, alongside building Retrieval-Augmented Generation pipelines with vector databases. Key responsibilities include optimizing CPU-based inference, managing model quantization, and ensuring enterprise-grade security and data privacy in air-gapped environments. The role offers the opportunity to deliver reference architectures and working prototypes while collaborating with internal teams on knowledge transfer. This position is ideal for engineers seeking to apply advanced AI technologies in a regulated industry setting with a hybrid work arrangement.