CUDA with C++ and Python Developer
Skill
- 5+ years of professional software development experience with strong focus on CUDA development.
- Strong proficiency in C/C++.
- Strong hands-on experience with Python, especially in scientific computing using PyTorch and NumPy.
- Experience working with CUDA version 12.3 or above.
- Strong understanding of GPU programming concepts, parallel computing, and performance optimization.
Availability
8 hours per day
Role Overview
We are looking for experienced CUDA Developers to work on cutting-edge AI and machine learning projects. In this role, you will contribute to improving large language model (LLM) capabilities by solving complex coding problems, optimizing GPU-based workloads, reviewing model-generated code, and helping train AI systems to produce high-quality CUDA and parallel computing solutions.
The ideal candidate should have strong expertise in CUDA, GPU programming, parallel computing, performance optimization, and Python-based machine learning ecosystems.
What does day-to-day look like:
- Solve advanced CUDA and parallel computing problems involving GPU acceleration and performance optimization.
- Review, evaluate, and improve AI-generated CUDA/C++/Python code.
- Analyze GPU kernel performance and optimize algorithms for throughput, latency, and memory efficiency.
- Work with CUDA libraries and frameworks such as Thrust, cuBLAS, and cuDNN.
- Develop high-quality prompts, solutions, explanations, and evaluations to improve AI model reasoning and coding performance.
- Debug and resolve issues related to CUDA kernels, memory management, synchronization, and resource utilization.
- Collaborate with cross-functional teams working on AI model training and evaluation.
- Stay updated with the latest developments in CUDA, GPU architectures, and parallel computing best practices.
Requirements:
- Bachelor's degree in Computer Science, Computer Engineering, or a related technical field.
- 5+ years of professional software development experience with strong focus on CUDA development.
- Strong proficiency in C/C++.
- Strong hands-on experience with Python, especially in scientific computing using PyTorch and NumPy.
- Experience working with CUDA version 12.3 or above.
- Strong understanding of GPU programming concepts, parallel computing, and performance optimization.
- Experience optimizing code for efficient resource utilization and high-performance execution.
- Familiarity with CUDA frameworks and libraries such as Thrust, cuBLAS, and cuDNN.
- Ability to solve complex technical problems independently.
- Strong written and verbal communication skills.
- Prior experience contributing to AI/ML systems or LLM-related projects is a plus.
Evaluation Process (approximately 60 mins):
- One round of Technical interviews
