Hybrid AI Architect & Lead — Edge & Cloud Inference

NIO; San Francisco (CA); On-site; USD 192,000 - 250,000; Full time

Benefits offered by this job

Medical plans

Dental & Vision

401(k)

Job summary

NIO Inc. in San Francisco is seeking a senior leader to architect Hybrid AI Vision, guiding a team across distributed systems orchestration and AI compiler engineering. This role focuses on distributing LLM/VLM workloads across edge/cloud environments and shaping the technical roadmap with an emphasis on resilience and performance.

The position requires a Ph.D. with 8+ years (or a Master with 12+ years) and strong hands-on expertise in LLM/VLM inference, model optimization, and production-grade

Qualifications

• Ph.D. with 8+ years or Master with 12+ years leading technical teams.
• Experience leading full-stack AI systems engineering.
• Hands-on mastery in at least two core domains with broad system view.

Responsibilities

• Architect Hybrid AI Vision and distribute LLM/VLM workloads.
• Lead, mentor, and guide a team across distributed systems and AI compilers.
• Design high-availability orchestration with dynamic model fallback and telemetry.

Skills

Leadership

Distributed systems

Inference optimization

C++

Python

Edge/Cloud architecture

Education

Ph.D. in CS/CE/AI

Master's degree in related field

Tools

vLLM

TensorRT-LLM

ExecuTorch

MLC-LLM

MLIR

Apache TVM

Triton

ONNX Runtime

llama.cpp

Job description

NIO Inc. in San Francisco is seeking a senior leader to architect Hybrid AI Vision, guiding a team across distributed systems orchestration and AI compiler engineering. This role focuses on distributing LLM/VLM workloads across edge/cloud environments and shaping the technical roadmap with an emphasis on resilience and performance.

The position requires a Ph.D. with 8+ years (or a Master with 12+ years) and strong hands-on expertise in LLM/VLM inference, model optimization, and production-grade