About the job
Core
Design and develop an on-premise Multi-Agent collaboration system architecture using Advanced RAG and multi-modal retrievers.
Role type
Senior Machine Learning Engineer (On-premise AI Agents & RAG)
Builds
Internal Multi-Agent collaboration system, specialized models, and AI pipelines.
Domain
Enterprise AI, On-premise Infrastructure, Retrieval-Augmented Generation
Deliverable
production ML models
Required skills
LLM architecture design, Python backend development, MLOps pipeline construction, AI Agent workflow design, on-premise model deployment and tuning
Preferred skills
RAG system optimization, Graph DB management (Neo4j, Memgraph), Kubernetes customization, cloud/on-premise GPU server management
Technologies
PyTorch, LangChain, Docker, SQL, Vector DBs (Milvus), Neo4j, Memgraph, k8s, AWS, Azure, GCP
Responsibilities
Design and develop on-premise Multi-Agent collaboration system architecture; Optimize Advanced RAG (Graph/Hybrid Multi-hop) and multi-modal retrievers; Conduct A/B tests for specialized models and pipelines; Establish best practices for on-premise code assistants.
Seniority
Senior, hands-on IC