Technical Staff(Scientist/Engineer) - Superintelligence Lab
수행 업무
AI Systems & Inference Infrastructure
Technical Staff responsible for designing, building, and scaling production-grade superintelligent AI agent systems and large-scale LLM inference infrastructure to support next-generation AI services.
본 포지션은 초지능 AI 에이전트 및 LLM 기반 서비스의 대규모 사용자 제공을 가능하게 하는 핵심 시스템 레이어를 담당합니다.
Tech Stack
- High-performance, large-scale distributed systems
- ML systems & infrastructure-level parallelism (data / tensor / pipeline)
- Dynamic autoscaling, load balancing, request routing, traffic shaping
- LLM inference optimization (batching, caching, KV-cache management)
- Kubernetes & cloud-native infrastructure
- Python, Rust
- LLM serving frameworks: SGLang, vLLM
Responsibilities
- Design and implement production-grade deployment pipelines for large-scale LLMs and AI agent services, supporting dynamic autoscaling and high availability
- Optimize LLM inference performance by implementing and integrating advanced techniques (e.g., batching, caching, scheduling, memory optimization) to reduce latency and improve throughput
- Build service-oriented architectures and well-defined APIs for scalable AI agent systems
- Design and maintain robust testing, benchmarking, and evaluation frameworks for performance, reliability, and system stability
- Collaborate closely with research teams to translate novel agent methodologies into deployable systems
Preferred Qualifications (Optional but Industry-Standard)
- Multi-year experience operating large-scale ML/LLM services in production
- Deep understanding of distributed systems and performance bottleneck analysis
- Familiarity with modern LLM serving stacks and GPU resource management
- Strong ownership mindset for reliability, scalability, and operational excellence
- Proof of transforming 0 (nothing) to 1 (something useful and innovative)
전형절차
- 서류심사 → 코딩테스트 & LG Way Fit Test → 1차 직무 인터뷰(온라인) → 최종 인터뷰(온사이트)
* 전형 절차는 변경될 수 있습니다. 서류 합격 시 전형 절차에 대해 별도로 안내 해 드립니다.
