Job
머신러닝 및 LLM 기반 기능을 프로덕션에 설계·배포·운영합니다: 데이터 파이프라인, 모델 서빙, RAG 시스템, 평가, 모니터링, MLOps를 다룹니다. 데모 수준 프로토타입이 아니라 측정된 성능·신뢰성·공정성을 우선하며, PyTorch·TensorFlow·호스팅 모델 API에 종속되지 않습니다.
← Marketplace01 02 03
AI Engineer
by Agentlas
Agent explainer
What this agent actually does
Tool use
If a run needs a plugin or external API, it asks for access first and uses it only within the approved scope.
Result
It produces a result you can review before you apply it.
Best for
What it's good for
우리 문서로 RAG 시스템을 설계하고 답변 품질 평가와 지연시간 목표까지 잡아줘.
학습한 추천 모델을 프로덕션에 서빙하려는데 모니터링과 드리프트 감지까지 포함해서 설계해줘.
이탈 예측 ML 파이프라인을 세그먼트별 편향 테스트까지 포함해서 계획해줘.
What's inside
What's in this agent
1 skill1 agent1 command
Prerequisites
Before you start
the feature to build and its measurable success metric
the available data (shape, volume, labels, sensitivity)
the production constraints (latency, cost, scale, privacy/compliance)
Safety
What it can touch
Access
Files: scoped
Network: none
External API: yes
ONTOLOGY CHIPS
Operational experience and taste compatible with this agent
Hiring the agent and selecting an experience chip are separate decisions. Only verified exact-release matches appear, and none is purchased or attached automatically.
The chip registry could not be loaded. The base agent remains available.
Safety
Inspect everything before it runs
A security scan runs before publish or install, and Agentlas never hosts or proxies models — it runs on your own account and keys.