AI Agent Engineer

Binance
Taipei
Workplace: HybridFull timeFunction: Data Science & Machine LearningExperience: 1+ yearsSkills: ["Problem-solving","Research","Rapid prototyping","Experiment iteration"]

Build and operate production retrieval and agent systems for next-generation LLM agents. You’ll engineer end-to-end RAG and Agentic RAG pipelines (embedding models, vector stores, hybrid search, reranking, chunking and parsing), design agent harness runtimes and retrieval-grounded tool calling, and prototype new ideas quickly. Work at the intersection of frontier model capabilities and real-world agent deployment, iterating based on real user feedback with fast experiment loops.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Binance
Binance
3 days ago

AI Agent Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 3 hours agoStatus: Live

Job Summary

Build and operate production retrieval and agent systems for next-generation LLM agents. You’ll engineer end-to-end RAG and Agentic RAG pipelines (embedding models, vector stores, hybrid search, reranking, chunking and parsing), design agent harness runtimes and retrieval-grounded tool calling, and prototype new ideas quickly. Work at the intersection of frontier model capabilities and real-world agent deployment, iterating based on real user feedback with fast experiment loops.
Location: Taipei
Workplace: Hybrid
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Entry level

Key Responsibilities

  • •Build end-to-end production retrieval pipelines for RAG and Agentic RAG, including embeddings, vector stores, hybrid search, reranking, and data parsing strategies.
  • •Implement Agentic RAG workflows such as Self-RAG, Corrective RAG, adaptive retrieval, multi-hop decomposition, and iterative retrieve-reflect-refine loops.
  • •Develop and operate agent harness runtimes and orchestration layers, including session recovery, sandbox isolation, multi-tenant execution, middleware/hooks, and plan/execute loops.
  • •Apply deep understanding of LLM and agent fundamentals—prompt/context engineering, agent loops, tool use, planning, memory, and multi-agent coordination—to ship effective agent behavior.
  • •Generate original ideas, run experiments, ship prototypes, and iterate fast using real user feedback in production scenarios.

Key Requirements

  • •1+ year hands-on experience building LLM, RAG, and AI agent systems in production.
  • •Build production retrieval pipelines end-to-end, including embeddings, vector stores, hybrid search, reranking, and chunking/text cleaning and multimodal parsing.
  • •Implement Agentic RAG patterns such as Self-RAG, Corrective RAG, adaptive retrieval, multi-hop decomposition, and retrieve-reflect-refine loops.
  • •Engineer agent harness runtimes and orchestration frameworks (e.g., Pi Agent, AgentScope 2.0), including session recovery, sandbox isolation, middleware/hooks, multi-tenant runtime, plan/execute loops, and retrieval-grounded tool calling.
  • •Deep familiarity with LLM and agent mechanisms including LLM APIs, KV cache, agent loops, tool use, prompt/context engineering, MCP, memory, subagents, and multi-agent coordination.
Experience:1+ yearsLLMRAGAI agentsAgentic RAGProduction systems
Skills:Problem-solvingResearchRapid prototypingExperiment iteration
Tech Stack:LLMRAGAgentic RAGEmbedding modelsOpenAIBGEVector storesQdrantMilvusPineconeWeaviateHybrid searchReranking modelsSelf-RAGCorrective RAGRetrieve-reflect-refinePi AgentAgentScope 2.0Orchestration frameworksSession recovery

Company Brief

Binance
Operates one of the world’s largest cryptocurrency exchanges, offering spot and derivatives trading, a native token (BNB), wallet services, staking, and a broad suite of crypto financial products and infrastructure.
Industry: Trading Platforms
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Established Company
Valuation: Unicorn (USD 1B+)
Funding: Bootstrapped
Headquarters: George Town, Cayman Islands
Founded: 2017
WebsiteLinkedIn