C++ Developer- CUDA and Linux (Mandatory Skills)

Job Description

Required Skills: C++: Strong proficiency in modern C++ (C++11/14/17/20). CUDA Programming: Extensive experience in developing, debugging, and optimizing CUDA applications. GPU Optimization: Familiarity with memory hierarchy, shared memory, streams, and warp-level operations in CUDA. Parallel Computing: Solid understanding of parallel algorithms and multi-threaded programming. Mathematical and Analytical Skills: Strong foundation in linear algebra, calculus, and numerical methods. Tools: Experience with debugging/profiling tools like Nsight, CUDA Memcheck, or similar Primary Responsibilities: Software Development: Develop and maintain high-performance applications using C++ and CUDA. Design and implement parallel algorithms for GPUs to accelerate computational workloads. Performance Optimization: Optimize CUDA kernels for performance, scalability, and memory efficiency. Analyze performance bottlenecks and propose innovative solutions. Code Review and Testing: Conduct code reviews to ensure adherence to coding standards and best practices. Develop and execute test cases to validate functionality and performance. Collaboration: Work closely with the software engineering and research teams to understand requirements and deliver robust solutions. Provide technical guidance and mentoring to junior team members when necessary. Documentation: Write and maintain technical documentation, including design specifications and user manuals Job Types: Full-time, Permanent Pay: ₹1,000,000.00 - ₹1,400,000.00 per year Schedule: Day shift Morning shift Ability to commute/relocate: Kandivali West, Mumbai, Maharashtra: Reliably commute or planning to relocate before starting work (Required) Application Question(s): This is an onsite (office) job. We are looking for a local MUMBAI candidates only for this role. Are you based out of Mumbai? Experience: C++ (C++11/14/17/20): 4 years (Required) CUDA Programming: 4 years (Required) GPU Optimization: 4 years (Required) Debugging/Profiling tools(Nsight, CUDA Memcheck etc): 4 years (Required) Work Location: In person