Daniel Pérez is a Senior AI DevTech Engineer based in Seville with 11 years building high-performance computing and AI solutions. Currently at NVIDIA, he blends deep interest in computational complexity with practical engineering to help developers optimize and scale AI workloads. His background emphasizes low-level performance tuning and system-level thinking, making him effective at translating research ideas into production-ready tooling. Colleagues describe him as someone who pairs rigorous problem-solving with a hands-on mindset, comfortable across GPU-accelerated stacks and developer-facing integrations. He brings a researcher’s curiosity to engineering trade-offs, often uncovering subtle performance bottlenecks others miss.
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Contributions:205 pushes, 27 branches in 1 year 2 months
Contributions:95 commits, 214 pushes, 31 branches in 3 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.