Alessio Netti
Senior AI Developer Technology Engineer at NVIDIA
Italy
Summary
👤
Senior🎓
Top SchoolAlessio Netti is an HPC AI Senior Research Engineer based in Bavaria with eight years of experience bridging high-performance computing, AI, and dependable system design. He holds a PhD from TUM and has driven production-scale monitoring and operational data analytics for large HPC centers at LRZ, later extending that expertise to hardware dependability research at Intel and applied HPC/AI work at DeepL. His work spans developing fault injection and benchmarking frameworks (FINJ, HDFIT) and optimizing hardware protections, reflecting a rare mix of software, hardware, and data-centre operational know-how. Alessio has also explored edge and satellite-enabled distributed systems during a stint at Siemens, showing a practical interest in non-traditional connectivity for IoT and industrial workloads. Comfortable with FPGA signal processing, systolic arrays, and AI-driven operations, he combines academic rigor with production engineering to harden and scale compute-intensive systems. An under-the-radar thread in his career is consistent focus on turning fault research into usable tooling that teams can deploy in real environments.
9 years of coding experience
5 years of employment as a software developer
Laurea Magistrale LM, Computer Science - Systems and Networks, Laurea Magistrale LM, Computer Science - Systems and Networks at Alma Mater Studiorum – Università di BolognaDoctor of Science, Computer Science, Doctor of Science, Computer Science at Technical University of MunichLaurea triennale, Computer Science, Laurea triennale, Computer Science at University of Naples ‘Parthenope’
English, Italian, German
Github Skills (10)
tensorrt10
cuda10
nvidia10
pytorch10
inference10
cpp10
runtimes10
large-language-models10
python10
llm10
Programming languages (2)
Github contributions (5)
AlessioNetti/fault_injector
Feb 2018 - Sep 2018
Contributions:70 commits, 64 pushes, 1 branch in 6 months
AlessioNetti/TensorRT-LLM
Oct 2024 - Jun 2026
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:13 pushes in 1 year 7 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.