Site Reliability Engineer — AI RAG & Agentic Systems

Binance; Philippines; Remote; PHP 1,200,000 - 2,400,000; Full time

Benefits offered by this job

Work-from-home arrangement

Job summary

Binance is seeking a senior AI/ML specialist to design and operate advanced retrieval and agent systems. You will work on Agentic RAG patterns, long-term memory, multi-agent architectures, and real-world task execution in a highly innovative environment.

The role emphasizes building production-grade retrieval pipelines with embedding models, vector stores, and hybrid search, while evaluating system performance and scalability in a remote setting.

Qualifications

• 2-8+ years hands-on experience with LLM, RAG and AI agent systems in production.
• Experience building production retrieval pipelines end-to-end with embedding models and vector stores.
• Experience with Agent Harness runtimes and multi-tenant orchestrations.

Responsibilities

• Design and operate retrieval pipelines with adaptive, multi-hop retrieval loops.
• Collaborate on model-capability-driven innovations including context management.
• Define benchmarks and evaluation methods for agent intelligence performance.
• Leverage real-world feedback to improve agent and retrieval performance in production.

Skills

LLM systems

RAG Engineering

Agent Harness

Prompt Engineering

Memory & Context Engineering

Multi-Agent Systems

Prototype to production

AI tooling proficiency

Tools

Qdrant

Milvus

Pinecone

Weaviate

OpenAI / BGE embeddings

Job description

Binance is seeking a senior AI/ML specialist to design and operate advanced retrieval and agent systems. You will work on Agentic RAG patterns, long-term memory, multi-agent architectures, and real-world task execution in a highly innovative environment.

The role emphasizes building production-grade retrieval pipelines with embedding models, vector stores, and hybrid search, while evaluating system performance and scalability in a remote setting.