Nvidia Cuda Engineer

Key Responsibilities
1. GPU Programming & Optimization
Develop, optimize, and maintain CUDA-based algorithms for high-performance applications.
Tune GPU kernels for maximum throughput, efficiency, and low-latency execution.
Implement parallel and distributed computation strategies for heterogeneous systems (CPU/GPU/FPGA).

2. Systems & Software Development
Build and maintain CUDA runtime libraries, drivers, and toolchain components.
Work on multi-processor system execution, memory management, and performance profiling.
Develop system-level software supporting NVIDIA GPU hardware.

3. Cross-Functional Collaboration
Partner with hardware engineers, architects, and product teams to design holistic GPU solutions.
Work with research teams on advanced real-time algorithms, AI workload acceleration, or CUDA-Q (quantum) frameworks.

4. CI/CD & Quality
Improve CI/CD pipelines for CUDA components.
Benchmark, validate, and enhance performance across software releases.

Required Skills & Qualifications
Technical Skills
Strong C/C++ programming skills (mandatory).
In-depth experience with CUDA, GPU architecture, performance tuning, and profiling tools.
Understanding of parallel programming paradigms (multi-threading, vectorization).
Experience with heterogeneous computing (CPUs, GPUs, FPGAs).

Preferred Skills:
Exposure to:
HPC systems
Compiler design (LLVM/MLIR)
Quantum-classical systems (CUDA-Q)
Distributed systems
Real-time algorithms and AI models

Experience
Bachelor's or Master’s in Computer Science/ Electrical/Electronics Engineering with
8+ years in GPU/CUDA software development (varies by role level).
Experience building robust, scalable production-grade systems.