[AI Frontier Div.] AI Native Full Stack Engineer (10년 이상)
Salary not listed • Seoul • Full-time
Posted 5mo ago
This job has been open for more than 60 days. It may no longer be actively hiring, so check with the company before putting a lot into an application.
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
The AI Frontier Division is an execution-focused organization that connects Krafton's core AI capabilities with tangible business results. We are seeking an AI Native Engineer who will leverage AI not just as an auxiliary tool, but as a core development partner. This role requires a senior engineer with experience in stably designing and operating services in high-traffic environments. The ultimate goal is to deliver stable and scalable services to customers by quickly adopting and applying new models and tools in the rapidly evolving AI landscape.
Responsibilities
- Take full ownership of the planning, development, deployment, and operation of AI-based products in collaboration with Product Owners within a Squad.
- Design and implement service features using AI models, including prompt design, API integration, RAG pipelines, MCP integration, and agent orchestration.
- Develop and operate end-to-end services spanning both front-end and back-end.
- Build, optimize, and ensure stable operation of model inference pipelines, including developing monitoring systems.
- Design and optimize service architectures for large-scale traffic environments.
- Design and operate CI/CD pipelines and data pipelines to ensure service stability.
Requirements
- Over 10 years of software development experience or equivalent expertise.
- Service development experience, primarily backend (Node.js/Python/Kotlin/Go), with the ability to understand the full service flow and structure complex requirements.
- Ability to independently design, review, and improve service architectures by translating product requirements into technical structures.
- End-to-end responsibility from planning to deployment and serving, with hands-on implementation to enhance completeness.
- Understanding of RDBMS and NoSQL databases, and ability to design data structures and access methods based on service requirements.
- Ability to make technical choices considering performance, security, stability, scalability, and cost, and explain the rationale.
- Proactive identification of technical risks and dependencies, and proposal of mid-to-long-term technical directions and improvement tasks.
- Experience designing and improving architectures and operational methods for large-scale traffic environments based on live service operations.
- Experience designing monitoring and observability systems (e.g., Datadog, Grafana) and leading root cause analysis, recovery, and recurrence prevention for incidents.
- Experience designing and improving CI/CD and infrastructure operation systems to enhance deployment stability and development productivity.
- Ability to define service level objectives and operational metrics, and establish operational standards including capacity, performance, and incident response.
- Ability to connect operational issues to structural improvement tasks, and propose priorities and execution plans.
- Experience using coding agents (e.g., Claude Code, OpenAI Codex, Cursor) as daily development tools, considering their strengths and limitations.
- Experience designing project contexts (e.g., CLAUDE.md, AGENTS.md, Rules) to manage agent output quality and consistency.
- Experience designing and operating agent execution environments and quality management systems, including tool permissions, safety constraints, and validation loops.
- Understanding of agent tool ecosystems (e.g., plugins, skill systems, MCP) and ability to design/develop custom tools or plugins.
- Experience designing and applying multi-agent systems or agent orchestration structures in actual development workflows.
- Ability to independently define ambiguous or complex problems, determine technical direction and solutions, and lead to implementation.
- Ability to document the background, alternatives, and trade-offs of key technical decisions and establish them as team technical standards.
- Ability to coordinate technical risks, schedule, and quality priorities for projects, and reach consensus with related departments and non-development roles.
- Ability to provide technical feedback on colleagues' designs and implementations, and improve the team's development capabilities and execution quality.
- Ability to proactively learn rapidly changing AI technologies and verify/apply them to actual products and development systems.
- No disqualifications for overseas business trips.