Alessandro Morari Email and Phone Number
Technical Leader and Researcher with over 15 years of experience in High Performance Computing (HPC) and Deep Learning. I am leading a team of specialists hands-on to accelerate AI software end-to-end, advancing NVIDIA's leadership in this space. My tenure includes spearheading the AI for Code research at IBM, which led to the creation of the Watson Code Assistant. In 2018, I contributed to developing the Summit and Sierra supercomputers, the world's fastest supercomputers. In 2014, I spearheaded PNNL's GEMS project, a high-performance, massively multithreaded graph database, which led to the spinoff of the startup Trovares.I developed and taught the first graduate course on HPC for Machine Learning at New York University. I have contributed to more than 30 academic publications and 15+ patents.
-
Leading Ai R And D @ Ai For Physics StartupStealth StartupUnited States
-
Developer Technology Engineer, Manager, AiNvidiaUnited States -
Developer Technology Engineer And Manager, AiNvidia Mar 2024 - PresentNew York City Metropolitan AreaHands-on technical leader of a team of AI and GPU specialists. Optimizing AI software end-to-end, from Deep Learning algorithms to low-level performance:- NeMo framework- PyTorch- TensorRT-LLM- Python, C++, CUDA
-
Co-Founder And AdvisorAtlantic Business Labs Inc. Jan 2022 - PresentFostering the US-Italian ecosystem. Technology Advisory. -
Advisory Board MemberNextstep Portfolios Llc Jun 2022 - PresentTechnology Advisory.
-
Senior Research Scientist, Tech Lead, Manager | Deep Learning & HpcIbm Jan 2019 - Mar 2024•Leading the implementation of GPU kernels with the Triton compiler•Evaluating Transformer memory footprint and scalability with Pytorch •Led the creation of a generative model based on CodeGen (PyTorch, Kubernetes, Docker, NVIDIA GPUs) that resulted in the Watson Code Assistant.•Led the application of BERT transformers to static analysis for C/C++ source code.•Led the application of ML and transformers to create a database for vulnerability detection extracting data from GitHub. -
Research Staff Member, Manager | High Performance ComputingIbm Jan 2017 - Dec 2018Greater New York City Area• Developed tools to reduce Linux OS noise for the Summit and Sierra supercomputers (world's fastest in 2018) successfully delivered to the Department of Energy (Linux OS).• Led the research and design of a novel high-performance runtime system enabling a global address space on a distributed cluster (C/C++).
-
Research Staff Member | High Performance ComputingIbm Apr 2016 - Dec 2016Greater New York City Area• Developed a tool to accurately measure the Linux OS noise on the Summit and Sierra supercomputers (Bash and C language).• Identified and solved performance bottlenecks deriving from the Linux OS activity.
-
Adjunct Professor - High Performance Machine LearningNew York University Jan 2018 - Dec 2018Greater New York City AreaDeveloped the first graduate course on High Performance technologies for Machine Learning. Topics: Python internals, PyTorch, NVIDIA CUDA, cuDNN, cuBLAS, MPI, GPUs, Multicore CPUs, high performance networks. The course is still being taught at NYU and other universities. -
Research Scientist | High Performance ComputingPacific Northwest National Laboratory Oct 2013 - Jan 2016Seattle• Developed the high-performance distributed index and SPARQL data ingestion engine for the GEMS distributed graph database (C/C++ language).• Developed a distributed and massively multithreaded runtime system (GMT see link in github) for the high-performance distributed RDF/SPARQL database GEMS (C language and x86 assembly). GEMS can perform queries with billions of RDF triples in seconds.• The project resulted in the spin-off of Trovares, a large scale graph analytics startup. -
Research Associate | High Performance ComputingPacific Northwest National Laboratory Jan 2012 - Sep 2013Richland/Kennewick/Pasco, Washington Area• Developed highly efficient parallel algorithms for the Tilera TILEPro 64 many-core processor (C language).
-
Researcher - Associate | High Performance ComputingBarcelona Supercomputing Center Jan 2009 - Dec 2011Barcelona Area, Spain• Developed tools to evaluate large scale Operating System noise on IBM Blue Gene P (C language).• Developed a performance model for multi-core architectures (Matlab). -
Software Engineer | Web DevelopmentI-Node S.R.L. Jan 2006 - Nov 2006Developed an advanced software framework to build PHP web applications.
Alessandro Morari Education Details
-
Computer Architecture -
Computer Engineering -
Computer Engineering
Frequently Asked Questions about Alessandro Morari
What company does Alessandro Morari work for?
Alessandro Morari works for Stealth Startup
What is Alessandro Morari's role at the current company?
Alessandro Morari's current role is Leading AI R and D @ AI for Physics Startup.
What schools did Alessandro Morari attend?
Alessandro Morari attended Universitat Politècnica De Catalunya, Università Di Roma Tor Vergata, Università Degli Studi Di Roma Tre.
Not the Alessandro Morari you were looking for?
-
Alessandro Morari
Italy -
-
Alessandro Morari
Italy -
Free Chrome Extension
Find emails, phones & company data instantly
Aero Online
Your AI prospecting assistant
Select data to include:
0 records × $0.02 per record
Download 750 million emails and 100 million phone numbers
Access emails and phone numbers of over 750 million business users. Instantly download verified profiles using 20+ filters, including location, job title, company, function, and industry.
Start your free trial