Gian Iodice
FPGA DeveloperAI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Distinguished Engineer @ Arm | Author | Speaker
Gian Marco Iodice is an edge and mobile computing distinguished engineer at Arm, focused on machine learning (ML). He authored the TinyML Cookbook and co-created KleidiAI (2024) and the Arm Compute Library (2017) software libraries to optimize ML performance on Arm processors. He received the MSc with honors in electronic engineering from the University of Pisa (Italy), where he specialized in HW/SW co-design for embedded systems. Within Arm, he leads the engineering developments for Generative AI. In 2023, he collaborated with the University of Cambridge to integrate ML functionalities on an Arm Cortex-M microcontroller powered by algae. Still, in 2023, Gian Marco contributed to developing the EdTech for Good Curation Framework. This framework, developed by UNICEF in collaboration with Arm and the Asian Development Bank (ADB), represents a significant step forward in the responsible use of technology in education because it enables public entities and international organizations to evaluate digital educational technologies, prioritizing learning outcomes and children’s safety. From 2022 to January 2024, he was chair of the global meetups for the tinyML foundation.
Università di Pisa
Master of Science (MSc), Electrical and Electronics Engineering
January 1, 2012 – January 1, 2014
Università di Pisa
Bachelor's degree, Electrical and Electronics Engineering
January 1, 2007 – January 1, 2011
Arm
Distinguished Engineer
April 1, 2026 – Present
tinyML Foundation
Chair of the tinyML global meet-ups
December 1, 2022 – May 1, 2024
Arm
Principal Software Engineer
April 1, 2022 – April 1, 2026
Packt
Book Author
May 1, 2021 – Present
United Kingdom
Arm
Staff ML Software Engineer for Machine Learning Group
October 1, 2018 – April 1, 2022
Arm
Senior ML Software Engineer for Machine Learning Group
April 1, 2017 – October 1, 2018
Arm
Computer Vision SW Engineer for the Visual Computing Team
January 1, 2016 – April 1, 2017
Arm
Graduate GPU Compute Engineer
September 1, 2014 – December 1, 2015
ARM
Summer Placement Student
July 1, 2013 – September 1, 2013
Greater Cambridge Area
Kalpa s.r.l.
Internship
April 1, 2013 – June 1, 2013
Milan, Lombardy, Italy
ARM Compute library: ARM Computer Vision & Machine Learning library for both ARM CPUs and ARM GPUs
March 1, 2017 – Present
The ARM Compute Library is a collection of low-level functions optimized for ARM CPU and GPU architectures targeted at image processing, computer vision, and machine learning. It is available free of charge under a permissive MIT open source license.
Using SGEMM and FFTs to Accelerate Deep Learning - Presentation at the May 2016 Embedded Vision Summit
May 1, 2016 – Present
Matrix Multiplication and the Fast Fourier Transform are numerical foundation stones for a wide range of scientific algorithms. With the emergence of deep learning they are becoming even more important, particularly as use cases extend into mobile and embedded devices. In this presentation we will discuss and analyze how these two key, computationally-intensive algorithms can be used to gain significant performance improvements for convolutional neural network (CNNs) implementations. After a brief introduction to the nature of CNN computations, we will explore the use of GEMM (General Matrix Multiplication) and mixed-radix FFTs to accelerate 3D convolution. We’ll show examples of OpenCL implementations of these functions and highlight their advantages, limitations and trade-offs. Central to the techniques explored will be emphasis on cache-efficient memory accesses and the crucial role of reduced-precision data types. http://www.embedded-vision.com/summit/using-sgemm-ffts-accelerate-deep-learning https://www.youtube.com/watch?v=pvuCg2yT5wY
Real-time Dense Passive Stereo Vision: Optimizing Computer Vision Applications Using OpenCL on ARM
May 1, 2015 – Present
The presentation was part of the Computer Vision on ARM Seminar held on 11 May, 2015 at the Santa Clara Convention Centre (US) http://community.arm.com/docs/DOC-10303 https://www.youtube.com/watch?v=hRFVUBBYNas Passive stereo vision is a powerful visual sensing technique aimed at inferring depth without using any structured light. Nowadays, as it offers low cost and reliability solutions, it finds application in many real use cases, such as natural user interfaces, industrial automation, autonomous vehicles, and many more. Since stereo vision algorithms are extremely computationally expensive, resulting in very high CPU load, the aim of this project is to demonstrate the feasibility of this task on a low power mobile ARM® Mali™ GPU. In particular, the implementation uses a local stereo vision method based on a novel extension of census transform, which exploits the highly parallel execution feature of mobile Graphic Processing Units with OpenCL. The presentation (https://www.youtube.com/watch?v=hRFVUBBYNas) shows up the approaches and the strategies used to optimize the OpenCL™ code in order to reach significant performance benefits on the GPU.
MP3 Player with scrolling menu on ARM® Cortex™-M3 (Beatstream 2.0)
March 1, 2012 – April 1, 2012
Beatstream 2.0: The Beatstream project started in July 2011 and is an hobby project. Some videos related to Beatstream 1.0 (wav player) are available on my youtube channel. Beatstream 2.0 was developed in March 2012 as upgrade of the previous implementation Beatstream 1.0. The project was sped over on ARM Cortex-M3 (STM32F1x MCU @72MHz, 512KByte Program Memory and 64KByte Data Memory). LCD controller: ILI9325 Touch Screen controller: TSC2046 (SPI protocol) MP3/WMA decoder: VS1003 It was used the SDIO periph. to inferface the microSD card to MCU. The MP3 player works without O.S. Beatstream 2.0 includes new features with respect to Beatstream 1.0 such as the Mp3/WMA decoder. It was developed from scratch in C with the only exception of FAT32 module where it was used the elm-chan FATFS (http://elm-chan.org/fsw/ff/00index_e.html). For the Beatstream 2.0 it was developed as well a new GUI. The GUI has a fast and responsive scrolling menu which is perfect for touchscreen devices. The scroll is composed by click (or touch) & drag scrolling with an additional movement after the finger is lifted off the screen.
Arm Expert - Developer program
Arm
June 24, 2026 – Present
Certificate of Completion "Rapid Development with Atmel AVR XMEGA and Atmel AVR Studio 5: Hands on Training"
Atmel Corporation
June 24, 2026 – Present
Cultural Fit Analysis
The candidate's extensive experience at ARM and involvement in open-source initiatives (ARM Compute Library) and community leadership (tinyML Foundation) suggest a strong cultural fit for organizations that value innovation, technical excellence, and knowledge sharing. The focus on optimizing performance for embedded and mobile devices aligns with a culture of efficiency and resourcefulness. However, the projects listed are primarily personal or related to previous roles, and there are no explicit projects directly related to FPGA development, which is the target role. This might indicate a gap in direct experience for the specific target role, potentially impacting cultural fit if the role requires immediate, hands-on FPGA design expertise.
Soft Skills & Operational Fit
The candidate's career progression at ARM, leadership role at tinyML Foundation, and experience as a book author suggest strong leadership, communication, and collaboration skills. The detailed project descriptions indicate a methodical approach to problem-solving and a commitment to optimizing performance, which aligns well with demanding technical roles. The long tenure at a leading embedded technology company like ARM suggests operational stability and a deep understanding of industry best practices.