Job description
VIPKid is seeking a Senior LLM Deployment & Inference Optimization Engineer in Singapore to build and manage self-hosted inference infrastructure for various AI-driven applications. You will design cloud inference services and improve performance management systems to enhance real-time interactions. The ideal candidate has a strong background in backend engineering, with over 5 years of experience, proven skills in optimizing inference techniques, and proficiency in tools like vLLM and TensorRT…