GenAI Engineer

About the Company STAFFXPERT LLC is seeking a GenAI Engineer on behalf of our client in Philadelphia, Pennsylvania. This role focuses on designing and implementing on-premise Large Language Model (LLM) solutions and vector database architectures. About the Role The ideal candidate will have strong hands-on experience with open-source LLMs, Retrieval-Augmented Generation (RAG) pipelines, and secure enterprise deployments. Responsibilities • Deploy and optimize open-source LLMs such as Llama 3 and Mistral / Mixtral in on-premise or private environments • Develop and integrate LLM-based applications using Python, including prompt engineering and inference workflows • Implement CPU-based inference, model quantization, and performance tuning techniques • Design and build scalable Retrieval-Augmented Generation (RAG) pipelines • Work with vector databases to manage embeddings, indexing, and metadata filtering • Ensure security, data privacy, and compliance in air-gapped or enterprise environments • Collaborate with cross-functional teams to deliver architecture, prototypes, and documentation Qualifications • Strong proficiency in Python for AI/ML application development • Hands-on experience with vector databases such as Qdrant, Chroma, Milvus, or pgvector • Proven experience implementing RAG solutions • Experience deploying LLMs in on-premise or secure environments • Strong understanding of embeddings, semantic search, and data pipelines • Knowledge of enterprise security practices, including access controls and audit logging Required Skills • Experience with LangChain or LlamaIndex • Familiarity with containerization tools such as Docker and Kubernetes • Exposure to inference frameworks like vLLM, llama.cpp, or Hugging Face Transformers • Experience with high-performance programming languages (Rust, Go, or C++) • Prior experience in regulated or enterprise environments Pay range and compensation package Contract (6+ Months) Equal Opportunity Statement We are committed to diversity and inclusivity.