6 days ago
Hyderābād, IndiaMid Level
Responsibilities
- Develop and commercialize the Qualcomm AI Runtime SDK on Qualcomm SoCs.
- Optimize inference performance for large generative AI models on CPU, GPU, and NPU accelerators.
- Build and maintain large C/C++ software stacks using software development best practices.
- Work with LLMs, LVMs, transformers, and edge-based generative AI deployment.
- Analyze performance, debug software, and collaborate across globally distributed teams.
Requirements
- Bachelor’s or master’s degree in computer science, engineering, information systems, or a related field.
- At least 3 years of relevant software development experience for the bachelor’s-degree path.
- Strong understanding of generative AI models, including LLMs, LVMs, and their building blocks.
- Knowledge of floating-point and fixed-point representations and quantization concepts.
- Experience optimizing algorithms for AI hardware accelerators such as CPUs, GPUs, and NPUs.
- Strong C/C++ development skills and analytical and debugging abilities.
- Preferred: knowledge of SIMD processor architecture, system design, object-oriented software development, Linux, Windows, SIMD kernel development, parallel computing, Assembly, llama.cpp, MLX, MLC, PyTorch, TFLite, and ONNX Runtime.
- Strong verbal, presentation, written communication, and collaboration skills.
Categories
About Qualcomm
Qualcomm is a public semiconductor company headquartered in San Diego, founded in 1985, that designs and sells wireless chipsets and platforms for mobile devices, automotive, IoT, and networking, notably the Snapdragon application processors and 5G modems. It also licenses a large portfolio of cellular patents to device makers, generating revenue alongside chip sales; its technology underpins many Android smartphones and emerging automotive and edge-compute systems, and it trades on NASDAQ as QCOM.