Engineer- AI/ML-tools

You will be joining the exciting Generative AI team at Qualcomm, focusing on integrating cutting-edge GenAI models on Qualcomm chipsets. The team utilizes Qualcomm chips" extensive heterogeneous computing capabilities to enable on-device inference of GenAI models without the need for a connection to the cloud. The inference engine is designed to allow developers to run neural network models trained in various frameworks on Snapdragon platforms at high speeds while consuming minimal power. Make use of the power-efficient hardware and software stack to run Large Language Models (LLMs) and Large Vision Models (LVM) at near GPU speeds. **Responsibilities:** - Spearhead the development and commercialization of the Qualcomm AI Runtime (QAIRT) SDK on Qualcomm SoCs. - Push the limits of performance from large models as an AI inferencing expert. - Deploy large C/C++ software stacks using best practices. - Stay updated on GenAI advancements, understanding LLMs/Transformers, and edge-based GenAI deployment nuances. - Embrace the role of edge in AI's evolution with passion. **Requirements:** - Master's/Bachelor's degree in computer science or equivalent. - 6+ years of relevant work experience in software development. - Strong understanding of Generative AI models like LLM, LVM, LMMs, and building blocks such as self-attention, cross-attention, kv caching, etc. - Knowledge of floating-point, fixed-point representations, and quantization concepts. - Experience with optimizing algorithms for AI hardware accelerators (e.g., CPU/GPU/NPU). - Proficiency in C/C++ programming, design patterns, and OS concepts. - Good scripting skills in Python. - Excellent analytical and debugging skills. - Effective communication skills (verbal, presentation, written). - Ability to collaborate with a globally diverse team and multiple interests. **Preferred Qualifications:** - Understanding of SIMD processor architecture and system design. - Proficiency in object-oriented software development and familiarity with Linux and Windows environments. - Strong background in kernel development for SIMD architectures. - Familiarity with frameworks like llama.cpp, MLX, and MLC. - Knowledge of PyTorch, TFLite, and ONNX Runtime. - Experience with parallel computing systems and languages like OpenCL and CUDA. Qualcomm is an equal opportunity employer committed to providing reasonable accommodations for applicants with disabilities. If you need an accommodation during the application/hiring process, reach out to disability-accommodations@qualcomm.com. Be assured that Qualcomm is dedicated to making the workplace accessible for individuals with disabilities.,