Description

Key Skills: Python, C++, PyTorch, TensorFlow, CUDA, LLMs, GPU Programming, AI/ML, Deep Learning, Model Optimization, Training & Inference

Roles & Responsibilities:

• Analyze AI and LLM architectures and map them to executable workloads.
• Design and develop optimized software components for AI frameworks.
• Improve training and inference performance, scalability, and reliability.
• Optimize throughput, latency, and memory utilization for AI workloads.
• Develop and maintain AI workload execution and benchmarking frameworks.
• Collaborate with hardware, compiler, kernel, and runtime teams.
• Implement and optimize GPU-accelerated AI solutions using CUDA.
• Validate workload accuracy and performance across different platforms.
• Support deployment and scaling of AI models in production environments.
• Identify and resolve performance bottlenecks in AI workloads.
• Contribute to framework enhancements and workload optimization strategies.
• Ensure efficient execution of large-scale AI and LLM applications.

Experience Required:

• 6-15 years of experience in AI/ML, Software Engineering, or Deep Learning.
• Strong programming skills in Python.
• Hands-on experience with PyTorch and TensorFlow.
• Strong understanding of LLM architectures and generative AI models.
• Experience implementing and optimizing AI training and inference workloads.
• Expertise in CUDA and GPU-accelerated computing.
• Knowledge of performance tuning, profiling, and workload optimization.
• Experience with distributed training and large-scale AI systems.
• Strong understanding of AI framework internals and execution pipelines.
• Experience in GPU programming and parallel computing.
• C++ development experience for performance-critical applications is preferred.
• Strong analytical, debugging, and problem-solving skills.

Education: B.Tech M.Tech (Dual), B.Tech

Key Skills

Education

Any Graduate