Staff AI Engineer
Core
Architect and lead the AI production stack for a customer engagement platform processing 4B+ messages/year, focusing on LLM orchestration, RAG, and agent infrastructure.
Role type
Staff AI Engineer (Senior IC)
Builds
Multi-provider LLM gateway, RAG pipelines, multi-agent workflows, and voice AI layer for real-time customer experiences.
Domain
Customer engagement / Conversational AI / Large Language Models
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, model fine-tuning
Technologies
OpenAI, Gemini, Qdrant, Milvus, Pinecone, WebRTC, LiveKit, GCP, AWS, Docker, Kubernetes
Responsibilities
Architect multi-provider LLM inference routing, design scalable RAG systems, lead voice AI evolution, own AI production lifecycles, optimize performance and costs, build evaluation infrastructure.
Seniority
Staff, high technical influence
