
// Open Role at Krafton
Lead Krafton's AI Inference Platform & Operations team, spearheading the design and operationalization of a robust serving platform for AI models. Optimize GPU resources and build a reliable framework to deliver groundbreaking gaming experiences globally.
우리는 게이머의 로망을 실현하기 위해, 누구도 가지 않는 길을 갑니다.
예상을 뛰어넘는 과감한 상상력과 기술로, 전 세계 팬들이 잊지 못할 세상을 만들기 위해 담대하게 도전하고 개척합니다.
We pioneer the path to players' dreams.
With bold imagination and breakthrough technology, we create unforgettable worlds for fans across the globe.
Inference fleet과 control plane 소유
조직 구축과 협업 구조 정립
안전한 모델 온보딩과 플랫폼 경험 제공
SLO와 운영 신뢰성 확립
GPU 자원과 단위 원가 관리
서빙 기법의 적용·튜닝과 서빙 시스템 개선
Agentic·실시간 음성 워크로드 효율화
Lead 역할
공통 기술 베이스
해외 출장에 결격 사유가 없는 분
Minimum 10+ years of experience in infrastructure, SRE, or platform engineering, with a proven track record of leading teams responsible for critical-path production systems. Proficient in selecting and justifying core technologies like serving engines and orchestration layers, balancing performance, cost, and operational complexity. Ability to directly design, review, and lead team execution for technical bottlenecks. Skilled in defining, improving, and making decisions based on latency, availability, throughput, and cost metrics. Experience negotiating SLOs and costs with business stakeholders and documenting technical decisions. Must have designed and operated large-scale distributed systems in Kubernetes (or equivalent) environments, covering deployment, load balancing, scheduling, autoscaling, observability, on-call, and incident response. Experience deploying and operating high-computation, low-latency real-time systems (LLM/ML serving, real-time 3D games) in production GPU environments. Practical experience with capacity planning, quota/priority, and resource isolation policies in dynamic, resource-constrained environments. Capable of writing production service code in Python or Go and modifying large open-source systems. Must have no disqualifying reasons for overseas travel.