Software Integration & Test Engineer

Qualcomm · Shanghai

Apply on the company website

Qualcomm Cloud AI is seeking an experienced Software Integration & Test Engineer to enable, validate, benchmark, and optimize large-scale AI workloads on Qualcomm Cloud AI accelerator platforms. You will work closely with architecture, runtime, compiler, kernel, and system software teams to deliver industry-leading AI performance and deployment readiness.

Key Responsibilities

• Integrate, deploy, and validate AI software stacks on Qualcomm Cloud AI platforms.
• Enable, deploy and evaluate state-of-the-art AI models, including LLMs, MoE, and multimodal models.
• Develop and execute functional, performance, and regression testing.
• Analyze performance bottlenecks and drive system-level optimization.
• Build and maintain automated test and validation frameworks.
• Collaborate across teams to ensure software quality, scalability, and release readiness.
• Support customer deployment, bring-up, performance tuning, debugging, and production readiness.

Required Qualifications

• Master's degree or above in Computer Science, Artificial Intelligence, Electrical Engineering, or a related field.
• Good verbal and written English communication skills to effectively collaborate across global teams.
• Strong experience with Python and Linux development environments.
• 5+ years of experience in Cloud AI, AI infrastructure, machine learning systems, or high-performance computing.
• Hands-on experience deploying and optimizing large language models in cloud environments.
• Strong understanding of Transformer architectures, LLMs, and MoE models.
• Experience with AI benchmarking, performance analysis, and workload characterization.
• Strong experience with one or more AI frameworks, including PyTorch, TensorFlow, ONNX, or JAX.
• Strong debugging, analytical, and problem-solving skills.

Preferred Qualifications

• Experience with inference frameworks such as vLLM, SGLang, TensorRT-LLM, TGI, LLM-D, or similar solutions.
• Experience with distributed inference, model serving, and large-scale AI deployments.
• Familiarity with model optimization techniques such as quantization, KV-cache optimization, and speculative decoding.
• Experience with Kubernetes, Docker, and cloud-native AI infrastructure.
• Experience with AI accelerator platforms (GPU, NPU, TPU, or custom AI hardware).
• Experience developing automated validation, regression, or CI/CD systems.

More jobs at Qualcomm · Software Engineering jobs in Shanghai