Design backend architecture for high-traffic AI-integrated services including LLM chatbots and animation generation.
Develop and operate APIs handling large-scale requests with optimized latency and cost constraints.
Identify performance bottlenecks and implement batching,caching,and queuing strategies.
What they want
Backend development experience of 2-5 years in production services.
Proficiency in Java,Kotlin,or Python for production service development and operations.
Direct experience handling traffic spikes and designing queuing,timeout,and backpressure policies.
Nice to have
Shipped LLM/GenAI services such as chatbots,agents,or image/video generation products.
Local model serving experience with vLLM,TensorRT,or Triton Inference Server.
Foundational knowledge and hands-on experience with PyTorch or TensorFlow.
Seoulstart's read
Visa tier (likely)
E-7 specialty / professional (likely)
Korean language
Native Korean fluency required
English friendliness
Medium: English JD, mixed-language workplace
Context
NAVER WEBTOON domestic chaebol affiliate based in Seongnam; Korean language requirement is explicit and typically non-negotiable for backend roles even with English-language JD; visa sponsorship for E-7 plausible but expect Korean fluency to be strongly verified during interviews.
This is Seoulstart's analysis of the public job description, not the employer's stated policy. Verify visa sponsorship, language requirements, and remote allowances directly with the recruiter.