About Us
KRAFTON pioneers the path to players' dreams. With bold imagination and breakthrough technology, we create unforgettable worlds for fans across the globe.
About the Team
The AI Frontier Division is an execution-driven organization that connects KRAFTON's core AI technology capabilities with tangible business results. Six Squads (In-game AI, Production AI, LLM AI, etc.) rapidly experiment and scale their respective businesses. We are looking for a Senior AI Native Engineer who utilizes AI not merely as a supplementary tool but as a core development partner, and simultaneously possesses experience in designing and operating services stably in high-traffic environments. As AI technology evolves rapidly, it's crucial to quickly learn new models and tools and apply them to production, but the ultimate goal is to create stable and scalable services and deliver them to customers.
Missions and Responsibilities
- Responsible for the entire process of planning, development, deployment, and operation of AI-based products in collaboration with the PO as part of a Squad (business execution unit).
- Design and implement service functionalities utilizing AI models (e.g., prompt design, API integration, RAG pipeline, MCP 연동, agent orchestration).
- End-to-End service development and operation spanning frontend and backend.
- Build and optimize model inference pipelines and develop monitoring systems for stable operation.
- Design service architecture and optimize performance in high-traffic environments.
- Design and operate CI/CD pipelines and data pipelines for service stability.
Required Experience and Qualifications
Service Development Capability (Core)
- 7+ years of software development experience or equivalent skill.
- Experience in Backend-centric service development (Node.js/Python/Kotlin/Go, one or more). Ability to understand the overall flow of a service.
- End-to-End service development experience, taking responsibility for the entire flow from planning to testing, deployment, and serving.
- Understanding and proficiency in RDBMS and NoSQL databases.
- Experience in designing and operating services with stability and scalability in mind.
Service Operation Capability
- Real-world service operation experience — experience deploying and stably operating services in high-traffic environments.
- Monitoring and incident response — experience from building a monitoring system to analyzing and resolving incidents (Datadog, Grafana, etc.).
- CI/CD and infrastructure operation — experience designing and operating automated deployment pipelines.
AI Native Development Capability
- Proficient in using coding agents like Claude Code, OpenAI Codex, Google Antigravity, Cursor as everyday development tools, understanding their strengths and limitations.
- Context & Harness Engineering experience — systematizing agent output quality through project context design (CLAUDE.md, AGENTS.md, Rules) and building agent runtime control systems (tool permission design, safety constraints, validation loops).
- Understanding of the agent tool ecosystem (plugins, skill systems, MCP - Model Context Protocol) and experience developing custom tools/plugins.
- Experience in multi-agent system design or agent orchestration is a plus.
Problem Solving and Collaboration
- Ability to independently perform problem definition to solution implementation.
- Habit of documenting technical decisions and sharing them with the team.
- Strong communication skills for smooth collaboration with non-development roles.
- High willingness to learn and adapt to rapidly changing AI technology trends.
- No disqualification for overseas business trips.
Preferred Qualifications
- Experience in cloud environments (AWS, GCP, Azure) and production-level architecture design, including Kubernetes (k8s), Docker, and IaC (Infrastructure as Code).
- Experience building GPU-based model serving infrastructure (vLLM, Triton) or implementing service features using open-source models.
- Experience operating AI services used by real users (DAU 100k+ or equivalent scale).
- Domain understanding of games, content, and user-centric services, or the ability to quickly learn new domains.
- Full-stack capabilities with Frontend (React, TypeScript, etc.) development experience.
- Experience as a Tech Lead or leading small teams.
- Even better if you:
- Have experience building a service from scratch to end using AI tools alone.
- Have a perspective of designing the entire environment an agent operates in, not just a single prompt.
- Always consider 'what value does this technology create for the business?'.
- Have experienced service failures and made systems more robust from that experience.
- Immediately try new AI models and find ways to apply them to production.
- Have a habit of documenting not only code but also architecture, experimental results, and decision-making processes.
- Enjoy finding and resolving performance bottlenecks.