Huazhe Tan

Algorithm Engineering Lead

ZOLOZ, an independent global trusted identity platform incubated by Ant Group (recommended in Gartner® reports), achieves annual revenue in the hundreds of millions. Focuses on overseas ToB security scenarios like eKYC, risk control, marketing, etc., with core algorithms covering face recognition, document recognition (OCR), AI Agent, and recommendation systems.

• Container Image Acceleration Optimization: Led the refactoring based on the OCIV2 image format, innovatively adopting file-system-level chunk storage, achieving over 80% reduction in storage resource usage. Designed an on-demand loading mechanism and P2P cache acceleration, enabling efficient management of large model files and second-level container startup, significantly improving cluster resource utilization and service response efficiency. Key contributions open-sourced, recommended by CNCF, and presented at the 2023 OpenAnolis OS Conference.
• Inference Performance Acceleration: Algorithm Orchestration Layer: Utilized DAG for multi-model parallelism and pre/post-processing optimization. Architecture Layer: Employed message queues to build integrated online/offline inference services. Model Layer: Implemented operator fusion and low-precision quantization, adapting to various inference frameworks and heterogeneous computing resources (Intel/ARM/AMD) for cost optimization. Hardware Level: Collaborated closely with Intel, ARM, and AMD teams to deeply exploit hardware potential. Achievements shared at the 2024 OpenAnolis OS Conference and 2024 Apsara Conference, receiving joint PR coverage from Alibaba Cloud and Intel.
• Large Model Inference System Design & Implementation: Built multi-level operator abstractions for heterogeneous hardware (GPU/CPU). Deployed a 1:N Parameter-Data separation architecture based on LWS, combined with large-batch decoding inference for cost optimization. Utilized TCP/RDMA for efficient KVCache transmission and elastic scaling in multi-cloud environments. Development Side: Established end-to-end CICD pipeline, integrating Prometheus+Grafana for comprehensive system monitoring. Operations Side: Leveraged Kubevela for unified resource management and operation of overseas multi-cloud, multi-site K8s clusters.
• Exploration of Overseas AI Applications: Actively expanded ToB application scenarios, including: minority language financial large models, enterprise-level Agent platform (integrating RAG, Workflow, MCP), intelligent document processing, large model-based risk control, AI-driven intelligent outbound calling systems, etc.