Software Intern - GPU Optimization 🎓

We are seeking a summer intern to join our advanced wafer inspection algorithm team, with a primary focus on GPU acceleration and CUDA code optimization. The intern will work on profiling, tuning, and redesigning CUDA kernels to maximize throughput and minimize latency in image processing and machine learning workflows used in semiconductor wafer inspection.

This role offers hands-on experience in high-performance computing. The intern will contribute to production-grade algorithm deployment, collaborating closely with algorithm engineers to integrate optimized GPU modules into real-time inspection pipelines.

Key Responsibilities:

• Design, implement, and optimize CUDA kernels for high-throughput image analysis and defect detection.

• Profile and tune GPU workloads using NVIDIA Nsight Compute, Nsight Systems, and other performance tools.

• Collaborate with algorithm engineers to integrate GPU/CUA optimized modules into inspection pipelines.

• Explore advanced optimization techniques such as memory optimization, thread and block configuration optimization, instruction-level optimization, kernel fusion and launch overhead reduction, algorithmic optimization and hardware-specific tuning.

• Analyze performance bottlenecks and propose architectural improvements.

• Document technical findings and present results to cross-functional teams.