AI Technical Lead
Core
Architect hybrid AI inference systems for smart electric vehicles, dynamically distributing LLM and VLM workloads across edge and cloud environments.
Role type
Senior IC AI Technical Lead (Hybrid Inference & Distributed Systems)
Builds
High-availability orchestration engines, cascading inference mechanisms, and robust telemetry for continuous inference under varying connectivity constraints.
Domain
Automotive / Autonomous Driving / Edge & Cloud AI
Deliverable
production ML models
Required skills
Distributed systems architecture, LLM/VLM inference optimization, model compression (PTQ, QAT, AWQ), hardware-aware compute optimization, AI compiler engineering, C++, Python
Preferred skills
Privacy-preserving AI techniques (federated learning, differential privacy), open-source contributions to ML infrastructure
Technologies
vLLM, TensorRT-LLM, ExecuTorch, MLC-LLM, MLIR, Apache TVM, Triton, FlashAttention, PagedAttention
Responsibilities
Architect hybrid AI vision systems, lead and mentor specialized engineers in distributed systems and inference optimization, design dynamic orchestration and resilience strategies
Seniority
Senior, hands-on IC with team leadership
