Sr. Lead engineer

Duties:

• Design, develop, and optimize CUDA-based algorithms for real-time processing in edge computing environments.
• Implement parallel computing solutions to enhance performance and efficiency of computer vision and machine learning applications.
• Collaborate with data scientists and engineers to translate machine learning algorithms into efficient CUDA implementations.
• Analyze and optimize existing algorithms and code to improve execution times and memory usage on NVIDIA GPUs.
• Mentor junior engineers and provide technical guidance on CUDA programming and optimization techniques.
• Collaborate with cross-functional teams, including hardware engineers, system architects, and product managers, to define project requirements.
• Stay updated with the latest advancements in CUDA programming, computer vision, and machine learning.

Required:

• Strong expertise in CUDA C/C++ programming with a deep understanding of GPU architectures and parallel computing principles.
• Experience with deep learning libraries and frameworks that support GPU acceleration (e.g., cuDNN, TensorRT).
• Proven experience in profiling and optimizing CUDA applications for performance and memory efficiency using tools like NVIDIA Nsight, Visual Profiler, or similar.
• Proficiency in computer vision algorithms (e.g., image processing, object detection, segmentation) and machine learning frameworks (e.g., TensorFlow, PyTorch).

Desired :

• Knowledge of embedded systems or real-time operating systems (RTOS) for deploying applications on edge devices
• Familiarity with data pipelines, data preprocessing, and handling large datasets efficiently.

Education:

• BE/BTech, Master’s or equivalent