Site Reliability Engineer
New
B
BinanceBlockchain
AsiaFull-TimeMiddle
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 2-8+ years
- Required Skills
- PythonMachine LearningPrompt EngineeringLLM
Requirements
- 2-8+ years of hands-on experience with LLM, RAG and AI agent systems in production.
- Experience building production retrieval pipelines end-to-end including embedding models, vector stores, hybrid search, and reranking models.
- Deep understanding of chunking strategy, text cleaning, and multimodal data parsing.
- Hands-on experience with Agent Harness runtimes such as Pi Agent or AgentScope 2.0.
- Deep familiarity with LLM and agent mechanisms like LLM APIs, KV Cache, Agent Loop, Tool Use, Reasoning, and Memory.
- Strong grasp of Prompt Engineering and Context Engineering.
- Ability to analyze ambiguous problems from first principles, generate original ideas, and drive research from 0 to 1.
- Proficiency in AI-assisted coding workflows and ability to learn new languages and frameworks rapidly.
Responsibilities
- Design and operate next-generation retrieval pipelines — moving beyond static retrieve-once patterns to adaptive, self-correcting, and multi-hop retrieval workflows.
- Architect Agentic RAG systems with dynamic retrieval control, query decomposition, iterative retrieve-reflect-refine loops, and multi-agent retrieval collaboration.
- Collaborate deeply with researchers and engineers to define and implement model-capability-driven innovations including context management, long-term memory, and multi-agent architectures.
- Propose harness-domain and RAG-domain benchmarks and evaluation methodologies, construct benchmark datasets, and measure agent intelligence.
- Leverage multi-channel user feedback and real-world task data to continuously improve agent and retrieval performance in production scenarios.
View Full Description & ApplyYou'll be redirected to the employer's site
