5 days ago
Kuala Lumpur, MalaysiaStaff+
Responsibilities
- Design and implement a unified AI gateway access layer, routing governance, and end-to-end observability system for multi-model, multi-cloud, and multi-vendor environments.
- Develop monitoring, security auditing, and automated management capabilities for AI data flows.
- Develop, performance-tune, and maintain gateway features including authentication, rate limiting, circuit breaking, canary releases, and protocol adaptation.
- Optimize high-concurrency, low-latency systems and improve disaster recovery, multi-cluster deployment, and elastic scaling.
Requirements
- Proficiency in at least one of Golang, Python, or Lua, with strong data structures, algorithms, and system-level programming skills.
- Familiarity with mainstream LLM API specifications and the ability to design multi-model integration solutions.
- Hands-on experience with streaming such as SSE and long-lived connection management.
- Strong understanding of TCP/IP, HTTP/HTTPS, HTTP/2, and gRPC.
- Familiarity with the internals or plugin development of at least one of Nginx, OpenResty, APISIX, or Kong.
- Strong independent execution, logical thinking, complex problem-solving, and collaboration skills.
Benefits
- Study Growth Fund supporting professional development and continuous learning.
- Internal team-building activities, workshops, and events.
- Global collaboration with an international team.
- Career advancement and internal mobility opportunities.
