1 day ago
Hyderābād, IndiaStaff+
Responsibilities
- Develop and commercialize the Qualcomm AI Runtime (QAIRT) SDK on Qualcomm SoCs.
- Optimize generative AI inference performance for large models on CPU, GPU, and NPU hardware accelerators.
- Build and maintain large-scale C/C++ software stacks using software engineering best practices.
- Deploy LLMs, LVMs, and other neural network models for power-efficient, on-device execution.
- Apply knowledge of transformers, self-attention, cross-attention, and key-value caching to edge AI systems.
- Collaborate with systems, hardware, architecture, test, and other engineering teams on system-level software solutions.
- Analyze, debug, and improve performance across Qualcomm’s heterogeneous computing platforms.
Requirements
- Bachelor’s degree in computer science, engineering, information systems, or a related field, or an equivalent master’s or PhD qualification.
- 6+ years of relevant software development experience.
- At least 2 years of experience with programming languages such as C, C++, Java, or Python.
- Strong understanding of generative AI models, including LLMs, LVMs, LMMs, self-attention, cross-attention, and key-value caching.
- Knowledge of floating-point and fixed-point representations and quantization.
- Experience optimizing algorithms for AI hardware accelerators such as CPUs, GPUs, and NPUs.
- Strong C/C++ programming, object-oriented design, design patterns, and operating-system knowledge.
- Strong Python scripting, analytical, debugging, communication, and collaboration skills.
- Preferred qualifications include SIMD processor architecture, system design, SIMD kernel development, Linux and Windows, PyTorch, TFLite, ONNX Runtime, OpenCL, CUDA, llama.cpp, MLX, and MLC.
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.