Added
5 hours ago
Type
Full time
Salary
Salary not provided

Related skills

rag llm agent pinecone milvus

📋 Description

  • Design and operate next-generation retrieval pipelines with adaptive, self-correcting, and
  • Architect Agentic RAG systems with dynamic retrieval control, query decomposition, iterate
  • Collaborate with researchers and engineers on model-capability-driven innovations including context
  • Work on harnessing agent tools in production, balancing research ideas with shipping prototypes and

🎯 Requirements

  • 1+ Year hands-on experience with LLM, RAG, and AI agent systems in production.
  • Experience building production retrieval pipelines end-to-end—embedding models, vector stores
  • Hands-on with Agent Harness runtimes (Pi Agent, AgentScope 2.0 or equivalent): session recovery
  • Deep familiarity with LLM & Agent fundamentals: APIs, memory, tools, reasoning, planning
  • Independent research capability; ability to translate ideas into runnable prototypes with rapid
  • Power user of agent products; strong judgment about model behavior; AI-native engineering mindset.

🎁 Benefits

  • Nice-to-have: experience with agent products (Claude Code, OpenClaw, Cowork, Manus) and RAG
  • GraphRAG/knowledge graph-augmented retrieval experience; Pi Agent/AgentScope 2.0 or other Agent
  • Kubernetes/EKS: pod isolation, resource management, secrets handling; security engineering: prompt
Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Related Engineering Jobs

See more Engineering jobs →