Key Responsibilities

• Full-Stack Development for AI Foundation Model Services

  • Build highly available and scalable inference services for LLMs/LMMs, including front-end interfaces, back-end APIs, task orchestration, and microservice governance.

• Data Annotation and Management Platform Development

  • Design and maintain multimodal annotation platforms (text / image / audio / video), supporting task distribution, quality assurance feedback, dynamic priority scheduling, and visualized monitoring.

• Model Deployment and Continuous Delivery

  • Develop DevOps/MLOps pipelines covering containerization, automated testing, canary release, A/B testing, and version rollback, ensuring rapid model iteration and reliable deployment.

Basic Requirements

• Proficient in JavaScript/TypeScript with frameworks such as React/Vue/Svelte; familiar with at least one backend language (Node.js / Python / Go / Java) and common web frameworks.

• Familiar with Docker, Kubernetes, and Helm; understanding of service mesh, au- to-scaling, and monitoring/alerting systems (Prometheus / Grafana / Loki).

• Skilled in modeling and optimization with MySQL/PostgreSQL and NoSQL databases (Redis/MongoDB/ClickHouse, etc.); knowledge of vector databases (Milvus / PGVector/ Faiss).

• Proficient with Git/GitHub/GitLab; experienced in unit, integration, and end-to-end testing; capable of producing clear technical documentation and collaborating across teams.