С++ / СUDA developer
Remote
Core
Implementation of complex computational algorithms on GPU and CPU with demanding latency and throughput requirements.
Role type
Senior IC C++/CUDA developer (high-performance computing)
Builds
High-performance GPU and CPU applications
Domain
High-performance computing / GPU acceleration
Deliverable
production ML models
Required skills
C++, CUDA, GPU programming, CPU programming, performance profiling, data structures, algorithms, object-oriented programming
Preferred skills
low-latency development, lock-free data structures, C programming, Linux drivers, Linux system internals, networking, memory optimization, inference optimization frameworks
Technologies
Nsight Systems, Nsight Compute, nvprof
Responsibilities
Implement complex computational algorithms on GPU and CPU; Refactor existing solutions to improve scalability
Seniority
Senior, hands-on IC