Bridging Agentic AI
to System Reality

Agent-Native Inference OS —
AI, SW, and HW on Memory-centric Infrastructure.


Co-Founders

Dongsoo Lee
Chief Executive Officer
Dongsoo Lee|이동수
  • National AI Strategy Committee Member | 국가인공지능전략위원회 위원

  • Ph.D. @ Purdue University·Memory Design, VLSI Testing, Emerging Memory
  • Research Staff Member @ IBM TJ Watson Research·Power9/10 CPU, NPU Design, FP8 Training
  • Principal Engineer @ Samsung Research·AI Model Compression Lead
  • EVP @ NAVER Cloud·AI Computing Strategy and Efficient Serving Systems
Minsoo Rhu
Chief Research Officer
Minsoo Rhu|유민수
  • Endowed Chair Professor @ KAIST·AI Computing System / GPU & NPU HW/SW Design
  • National AI Strategy Committee Member | 국가인공지능전략위원회 위원

  • Ph.D. @ University of Texas, Austin·GPU Processor and Memory System Design
  • Research Scientist @ Meta·Hardware/Software Systems for Secure and Private AI
  • Senior Research Scientist @ NVIDIA·GPU Memory Virtualization / AI Accelerator Design
  • Program Chair for MICRO 2025, MICRO/ISCA/HPCA Hall of Fame
Baeseong Park
Chief Product Officer
Baeseong Park|박배성

  • Engineer @ Samsung Research·Optimized Transformer Kernel
  • Leader @ NAVER Cloud·AI Serving System
Se Jung Kwon
Chief Strategy Officer
Se Jung Kwon|권세중

  • Ph.D. @ KAIST
  • Staff Engineer @ Samsung Research·Model Compression
  • Leader @ NAVER Cloud·AI-HW Partnership / Strategy
  • Adjunct Professor @ KAIST·NAVER-INTEL-KAIST AI Research Center

Build With Us

We're not hiring for headcount — we're looking for people who want to take on the Agent-native challenge from the ground up.
Here's the expertise we need:

a2sys는 단순히 인력을 채우기 위해 채용하지 않습니다. AI 시스템을 처음부터 다시 설계하는 Agent-native한 도전을 함께할 사람을 찾고 있습니다.
이를 위해 필요한 전문성은 다음과 같습니다:

Area Your Background Your Stack
Agent
Engineering
에이전트 엔지니어링

You own the Agent Studio and APIs. You implement, orchestrate, and evaluate agents iteratively — building the organization's agent capabilities while feeding workload data to other cores. You have strong opinions on how to run LLM-based tool-calling reliably at scale.

Agent Studio와 API를 관장합니다. 에이전트의 직접 구현·오케스트레이션·평가를 반복 수행하여 조직의 에이전트 역량을 누적하고, 그 과정에서 생성된 워크로드 데이터를 타 Core에 공급합니다. LLM 기반 tool-calling 구조를 신뢰할 수 있는 규모로 운용하는 방법에 대한 강한 의견이 있습니다.

Python FastAPI LLM APIs LangChain MCP Prompt Engineering
Model
Engineering
모델 엔지니어링

You oversee the company's research direction. You drive model architecture research, design KV-shareable model families, and build evaluation frameworks to ensure quality and reproducibility of model assets. You coordinate research priorities across engineering cores.

회사 전반의 연구 흐름을 총괄합니다. 모델 아키텍처 연구·개조, KV 공유 가능한 모델 패밀리 설계, 평가 체계 구축으로 모델 자산의 품질·재현성을 책임집니다. 전사 Engineering Core의 연구 우선순위를 조율합니다.

PyTorch SFT RL LLM Architecture Evals
System
Engineering
시스템 엔지니어링

You own the active KV optimization infrastructure. You build and operate training and serving infrastructure with KV-compatible, pooling-based inference stacks — converting model assets into real cost and latency advantages.

능동형 KV 최적화 인프라를 관장합니다. 학습·서빙 인프라와 KV 호환·풀링 기반 inference stack을 구축·운영하여 모델 자산을 실속 가능한 cost·latency 우위로 전환합니다.

Python LLM Inference CUDA Kubernetes Docker
Hardware
Engineering
하드웨어 엔지니어링

You lead the next-generation memory stack. You drive co-design collaborations with memory vendors to propose and build memory hierarchy structures optimized for agentic workloads.

차세대 메모리 스택을 주도합니다. 메모리 회사와의 co-design 협업을 주관하여 에이전트 워크로드에 최적화된 메모리 계층 구조를 선도·제안합니다.

C++ GPU Architecture Memory Systems Co-design

Don't see your role? We'd still love to hear from you.


Contact

Questions about a2sys, hiring, or partnerships? Send us a message.
회사, 채용, 파트너십 관련 문의는 편하게 남겨 주세요.

Hiring Partnership & Business Technical Collaboration General Inquiry
Get in Touch