Senior System Software Engineer - AI

Key Skills

Aartificial intelligence, Algorithms, Analytical and Problem solving, C++, CUDA/GPU programming, Deep Learning, Effective communication skills, Machine learning techniques, PyTorch, TensorRT

Job Description

There is a growing emphasis on processing AI computations at the edge, closer to the source of data. This approach reduces latency, enhances real-time processing, and addresses privacy concerns by minimizing the need for sending data to centralized servers. As technology continues to advance, we can expect client-side AI (local execution) to play a pivotal role in shaping the digital landscape. The Windows AI team (WinAI) is currently in search of a Senior Systems Software Engineer who is passionate about tackling the challenges linked to client-side AI on Windows PCs, navigating complexities such as limited compute and memory resources, and ensuring seamless integration and execution of inference workloads across locally available devices (like GPUs, and NPUs) and cloud.

What You’ll Be Doing:

• Design and implement a highly performance optimized framework for running AI NPCs in gaming applications as part of the NVIDIA ACE Platform through CUDA-DX interop

• Develop a Hybrid AI platform which can execute AI inferencing seamlessly across cloud and local devices supporting different ML backends like TensorRT, ONNX RT, DirectML, PyTorch etc.

• Identify and implement compute and memory optimizations across the full inferencing stack – HW scheduling, driver, backends and model pipelines to ensure the best performance and quality of service

• Collaborate with AI application developers from different focus areas – gaming, creator, and productivity– to develop inferencing platforms targeting high developer adoption.

• Collaborate with Microsoft to drive the advancements in APIs, AI frameworks, and platforms for developing and deploying AI inferencing applications.

• Ensure the effective deployment of directed tests through collaboration with the automation team, thereby ensuring the robustness of automated testing.

What We Need To See:

• Bachelor's, Master's, or PhD in Computer Science, Software Engineering, Mathematics, or a related field (or equivalent experience).

• 5+ years of proven experience with proficiency in AI inferencing pipelines and applications using ML/DL frameworks like TensorFlow, PyTorch, ONNX RT, DirectML etc.

• Excellent C++ programming and debugging skills with a strong understanding of data structures and algorithms.

• Strong analytical and problem-solving abilities, with the capacity to multitask effectively in a dynamic environment.

• Outstanding written and oral communication skills, enabling effective collaboration with management and engineering teams.

Ways To Stand Out From The Crowd:

• Understanding of modern techniques in Machine Learning, Deep Neural Networks, and Generative AI with relevant contributions to major open-source projects will be a plus.

• Consistent track record of delivering end-to-end products with geographically distributed teams in multinational product companies.

• Proficiency in lower-level system/GPU programming, CUDA, developing high performance systems

• Hands on experience with building applications using graphics APIs like OpenGL, DirectX, Vulkan