Q

Qualcomm

Designs mobile chips and licenses wireless patents

Camera AI Engineer - IoT, Software Engineering

Applied Machine LearningConfirmed live in the last 24 hours
Full-timeGuangdong Province, ChinaNo salary listedIn-person

About the Job

Requirements

  • At least 3 years of hands-on experience in machine learning model deployment, optimization, or embedded AI development on IoT, mobile, or real-time embedded platforms.
  • Strong proficiency in Python and C/C++, including performance-critical, system-level programming and machine learning tooling workflows.
  • Solid understanding of deep learning model architectures, including CNNs, transformers, large language models, diffusion, and multimodal models, and common frameworks such as PyTorch, TensorFlow, and ONNX.
  • Knowledge of model optimization techniques, including quantization (PTQ/QAT), pruning, graph optimization, and hardware-aware model design, with analytical and debugging skills for accuracy and performance issues on real hardware.
  • Bachelor's degree in Computer Engineering, Computer Science, or Electrical Engineering.
  • At least 2 years of Software Engineering or related work experience with a Bachelor's degree in Engineering, Information Systems, Computer Science, or a related field; or at least 1 year with a Master's degree in those fields; or a PhD in those fields.
  • At least 2 years of academic or work experience with a programming language such as C, C++, Java, or Python.

Responsibilities

  • Support Model Onboarding requests from Qualcomm customers in China, driving each request from intake through production deployment across large language models, generative AI, vision, audio, and multimodal models.
  • Analyze and adapt customer models by reviewing architectures such as CNNs, transformers, large language models, diffusion, and multimodal networks, identifying unsupported operators or structures, and adapting models for efficient execution on Qualcomm hardware.
  • Quantize, convert, and compile models from frameworks such as PyTorch, TensorFlow, and ONNX into Qualcomm runtime formats using QAIRT and related Qualcomm AI tools; apply PTQ/QAT and large language model and generative AI techniques, including weight-only, activation, and KV-cache quantization, mixed precision, LoRA, and batching, to meet targets.
  • Validate model inference through x86 reference simulation and on-device testing, checking numerical correctness and functional behavior on the Hexagon NPU (HTP).
  • Debug and fine-tune accuracy and performance by analyzing quantization error and layer-wise mismatches, profiling latency, memory, and power (including large language model token rates and KV-cache footprint), and applying hardware-aware tuning to meet customer KPIs.
  • Collaborate with Qualcomm model, tool, framework, and SDK teams to align onboarding solutions with SoC and HTP capabilities and escalate gaps in operator or feature support.
  • Participate in the Software Development Life Cycle, including requirement analysis, design reviews, development, testing, integration, debugging, and performance tuning.

Desired Qualifications

  • Master's or PhD in Computer Engineering, Computer Science, or Electrical Engineering.
  • Hands-on experience with Qualcomm AI SDKs such as QAIRT (Qualcomm AI Runtime SDK) or Hexagon SDK, and deploying models on Snapdragon using the Hexagon NPU (HTP) or Adreno GPU.
  • Experience optimizing or deploying large language models and generative AI models such as LLaMA, Qwen, Mistral, Stable Diffusion, or similar VLM/LMM families, including weight-only and KV-cache quantization for on-device inference.
  • Familiarity with on-device and generative AI inference runtimes such as Llama.cpp and LiteRT, and with tensor layouts, transformations, and tensor-processing mathematics.
  • Experience using AI coding agents and assistants such as GitHub Copilot, Claude Code, and Cursor to accelerate development, debugging, and tooling workflows.

About the Company

Qualcomm

Designs mobile chips and licenses wireless patents

Qualcomm designs the Snapdragon processors and modems inside many Android phones, and it licenses its wireless patents to device makers around the world. It helped commercialize CDMA, the cellular technology behind 3G networks, and its patents cover core parts of the 4G and 5G standards that phones use to connect. The company does not run its own chip factories; contract foundries make its chips, which it sells to makers of phones, PCs, cars, and connected devices. Device makers also pay Qualcomm royalties for using its patented technology, which forms a second business alongside chip sales. Qualcomm was founded in 1985 and is based in San Diego, California.

Company size
10,001+
Company stage
IPO
Headquarters
San Diego, CA
Founded
1985

Recently Posted Jobs

Explore more opportunities at Qualcomm

See more jobs