CareerPlanSign in

Staff AI Engineer

Shenzhen, Guangdong Province, China💼 Full-time🗓 2026-04-09 → 2026-09-26

Core

Architect and lead the production stack for LLM orchestration, RAG, and agent infrastructure at 4B+ messages/year scale.

Role type

Staff AI Engineer (LLM Infrastructure & Agentic Systems)

Builds

Multi-provider LLM gateway, RAG pipelines, multi-agent workflows, and voice AI layer

Domain

AI/ML infrastructure, conversational AI, real-time messaging platforms

Deliverable

production ML models

Required skills

Go, Rust, C++, Python, LLM orchestration, RAG architecture, vector databases, agentic frameworks, real-time voice pipelines, Infrastructure-as-Code

Preferred skills

Multi-agent orchestration, MCP protocols, WebRTC, GCP/AWS, Docker, Kubernetes

Technologies

OpenAI, Gemini, Qdrant, Milvus, Pinecone, WebRTC, LiveKit, GCP, AWS, Docker, Kubernetes

Responsibilities

Architect multi-provider LLM inference routing, design scalable RAG and multi-agent systems, optimize API costs and latency, build automated data pipelines for fine-tuning, establish AI quality evaluation infrastructure, drive technology roadmap decisions

Seniority

Staff, hands-on IC with significant technical influence

Sourced via workable · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.