Software Engineer, AI Large Model Platform

Responsibilities

Team Introduction
We are building an automated moderation and risk control system for international monetization, aiming to create a highly available and scalable Agentic System that horizontally supports risk control, user experience, and operational efficiency, while vertically consolidating a self-iterating closed-loop capability centered on policies. The platform needs to handle hundreds of millions of daily tasks and collaborate closely with product, operations, development, and algorithm teams to form an end-to-end solution from strategy generation and machine moderation execution to attribution optimization.

Responsibilities
1. Design and implement a high-availability, high-concurrency automated review system capable of handling hundreds of millions of daily tasks.
2. Build a large model platform covering the complete lifecycle from model training, evaluation, and version control to online deployment and monitoring, improving model development and operational efficiency.
3. Develop a strategy platform, leveraging cutting-edge Agent technology to create an industry-leading Agentic System.
4. Collaborate with product, operations, development, and algorithm teams to define problems and evaluation metrics, and formulate implementation plans and evolution roadmaps.

Qualifications

Minimum Qualification(s):
- Bachelor's degree or higher in computer science or a related field.
- Solid foundation in data structures, design patterns, and algorithms, with a focus on high-availability, scalable, and observable architecture design and elegant code.
- Familiarity with common components and practices of distributed systems: data storage, caching mechanisms, message queues, batch/stream processing, and big data processing.
- Understanding and ability to apply technologies such as Prompt Engineering, RAG, MCP, A2A, Agent architecture, and Harness Engineering, with the capability to deploy LLMs in real business scenarios, focusing on robustness, cost, and quality trade-offs.
- Programming language proficiency is flexible, with preference for Golang or Python; strong code quality and testing awareness.
- Good product thinking, able to proactively consider product and technical solutions based on business goals.

Preferred Qualification(s)
- Experience in building Multi-Agent systems, MCP, or strategy platforms.