Job Brief

We are looking for a seasoned Developer with deep expertise in C++, CUDA programming, and Linux environments to provide technical leadership and drive the development of advanced solutions in device integration and high-performance computing.
Responsibilities
- Immediate Joiners only, candidate should join within 15 days
- Work Mode - Work from Office
- Develop high-performance applications using C++ and CUDA
- Implement parallel GPU algorithms to speed up computations.
- Optimize CUDA kernels for speed, scalability, and memory use.
- Identify bottlenecks and suggest performance improvements.
- Review code for quality and adherence to standards.
- Create and run tests to validate functionality and performance.
- Collaborate with engineering and research teams on requirements.




- Mentor junior developers and offer technical guidance.
- Write and update design specs and user documentation.

Requirements
- Skilled in modern C++ standards including C11, C14, C17, and C20
- Experienced in building, debugging, and optimizing CUDA applications
- Familiar with CUDA memory hierarchy, shared memory, streams, and warp-level operations.
- Solid grasp of parallel algorithms and multi-threaded programming.
- Solid foundation in linear algebra, calculus, and numerical methods.
- Proficient with tools like Nsight, CUDA Memcheck, and other profiling utilities

📌 C++ Developer (Mumbai)
🏢 KSmart Staffing Solutions
📍 Mumbai