Design and implement LLM-based planning,tool-calling,and multi-step reasoning structures for AI agents
Design and optimize agent memory modules covering short-term,long-term,and retrieval-augmented memory
Design agent workflow orchestration and state management architecture
What they want
Hands-on experience with Python-based deep learning frameworks,particularly PyTorch
Practical experience applying at least one agent framework such as LangChain,LangGraph,or AutoGen
Implementation experience with agent components including planning,tool-calling,and memory systems
Nice to have
Debugging experience with observability tools such as LangSmith,Langfuse,or Weights and Biases
Healthcare AI or medical domain project experience with basic understanding of medical terminology
Multi-agent system design experience
Seoulstart's read
Visa tier (likely)
E-7 specialty / professional (likely)
Korean language
Business-level Korean required
English friendliness
Medium: English JD, mixed-language workplace
Context
NAVER AI Agent engineering role in healthcare verticalized domain; large GPU infrastructure and end-to-end research-to-production scope rare globally; Korean proficiency expected for clinical collaboration and regulatory navigation despite English-language JD.
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.