CareerPlan

AI Software Engineer

Guangdong, ChinaFull-time2026-11-17 → 2026-11-19

Core

Enable, optimize, and deploy state-of-the-art AI models (LLMs, VLMs, Diffusion, MoE) on edge platforms, focusing on performance, memory efficiency, and accuracy.

Role type

Senior IC AI Model Optimization Engineer

Builds

Automated and intelligent model onboarding, conversion, deployment, and optimization pipelines for on-device execution

Domain

Edge AI / Mobile / Embedded Systems

Deliverable

production ML models

Required skills

Deep learning fundamentals, Transformers, PyTorch, ONNX, model quantization (INT8/INT4, PTQ, QAT), model export/conversion, graph transformation, compilation, runtime execution, profiling, Python programming, hardware-aware optimization

Preferred skills

LLM/VLM/Diffusion/MoE optimization, heterogeneous computing (CPU/GPU/NPU/DSP), advanced quantization (INT4/INT2, GPTQ, AWQ, SpinQuant), system-level optimization, automated pipelines, research experience

Technologies

PyTorch, ONNX, PTQ, QAT, LLMs, VLMs, Diffusion Models, MoE

Responsibilities

Enable and optimize AI models for on-device deployment; Develop automated model onboarding and optimization pipelines; Work on end-to-end model enablement (export, quantization, compilation, runtime); Analyze performance bottlenecks across model, software, and hardware; Explore optimization for emerging model architectures; Investigate platform-aware optimization; Evaluate emerging technologies and translate to practical solutions

Seniority

Senior, hands-on IC