Backend Engineer - Large Model Knowledge System/Content Understanding/Rag (Bytedance Singapore)

About Us Founded in 2012, ByteDance's mission is to inspire creativity and enrich life. With a suite of more than a dozen products, including TikTok, Lemon8, CapCut and Pico as well as platforms specific to the China market, including Toutiao, Douyin, and Xigua, ByteDance has made it easier and more fun for people to connect with, consume, and create content.​ Why Join ByteDance Inspiring creativity is at the core of ByteDance's mission. Our innovative products are built to help people authentically express themselves, discover and connect – and our global, diverse teams make that possible. Together, we create value for our communities, inspire creativity and enrich life - a mission we work towards every day.​ As ByteDancers, we strive to do great things with great people. We lead with curiosity, humility, and a desire to make impact in a rapidly growing tech company. By constantly iterating and fostering an "Always Day 1" mindset, we achieve meaningful breakthroughs for ourselves, our Company, and our users. When we create and grow together, the possibilities are limitless. Join us.​ Diversity & Inclusion​ ByteDance is committed to creating an inclusive space where employees are valued for their skills, experiences, and unique perspectives. Our platform connects people from across the globe and so does our workplace. At ByteDance, our mission is to inspire creativity and enrich life. To achieve that goal, we are committed to celebrating our diverse voices and to creating an environment that reflects the many communities we reach. We are passionate about this and hope you are too.​ Job highlights Positive team atmosphere Responsibilities About The Team The Volcano Engine Vector Database Knowledge Base team supports both internal and ToB customer requirements. We are responsible for the massive content processing of the Volcano Engine large model knowledge base and the effect tuning, evaluation and monitoring, and algorithm architecture optimization of the retrieval system architecture. We also provides technical solutions in framework construction, new feature delivery, and vertical solution construction. Responsibilities 1. Build and iterate the multimodal content understanding pipeline, resolve service availability, throughput, and storage bottlenecks to improve development efficiency. 2. Optimize vector computing components and model inference performance, and implement large-scale vector retrieval and video representation models for massive video content. 3. Design and optimize large model RAG and knowledge base architecture, and deliver general domain knowledge base solutions for public cloud products. 4. Maintain and extend the backend architecture of in-house vector databases to support multimodal unstructured data processing and storage. 5. Drive iteration of cloud-native capabilities including monitoring, billing, and elastic scheduling for vector database and knowledge base services. Qualifications Minimum Qualifications 1. Bachelor’s degree in Computer Science or a related field. 2. 3+ years of professional software development experience in backend, AI infrastructure, or cloud services. 3. Solid programming skills in at least one of Python/C++/Golang/Java, with strong problem-solving abilities. 4. Basic understanding of large model applications and RAG systems, with passion for AI and cloud implementation. 5. Good communication and collaboration skills, proactive in tackling challenging problems. Preferred Qualifications 1. Experience in recommendation, search, advertising, recall or ranking systems. 2. Familiarity with PyTorch/TensorFlow; experience in high-performance computing or CUDA. 3. Knowledge of high-concurrency, high-throughput system design; cloud or database experience. 4. Experience contributing to open-source projects.