Engineer, -AI and Machine Learning with embedded/C++

Role Overview

As a leading technology innovator, Qualcomm pushes the boundaries of what's possible to enable next-generation experiences and drives digital transformation. As a Qualcomm Software Engineer, you will design, develop, create, modify, and validate embedded and cloud edge software, applications, and/or specialized utility programs. This role is strictly for AI/ML inference SDK development on embedded systems, focusing on integrating cutting-edge GenAI models on Qualcomm chipsets using heterogeneous computing capabilities.

Responsibilities

• Spearhead the development and commercialization of the Qualcomm AI Runtime.
• Push the limits of performance from large models as an AI inferencing expert.
• Deploy large C/C++ software stacks using industry best practices.
• Stay on the cutting edge of GenAI advancements, including LLMs and Transformers.
• Optimize edge-based GenAI deployment.

Requirements

• Master’s/bachelor’s degree in computer science or equivalent.
• 9-15 years of relevant work experience in software development.
• Strong proficiency in C++ programming, Design Patterns, and OS concepts.
• Experience optimizing algorithms for AI hardware accelerators (CPU/GPU/NPU).
• Understanding of Generative AI models (LLM, LVM, LMMs) and building blocks like self-attention, cross attention, and kv caching.
• Knowledge of Floating-point, Fixed-point representations, and Quantization concepts.
• Excellent analytical and debugging skills.

Skills

• C++
• Python
• Embedded Systems
• AI/ML Inference
• Generative AI

Nice to Have

• Strong understanding of SIMD processor architecture and system design.
• Proficiency in object-oriented software development.
• Familiarity with Linux and Windows environments.
• 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.