Explore every episode of the podcast AI with Sally Ward-Foxton

On Axelera's fifth anniversary, CEO Fabrizio del Maffeo discusses funding, talent, RISC-V, edge AI and why Europe needs to think bigger.

In this podcast, Tensordyne’s Gilles Backhus explains why the company abandoned conventional arithmetic in pursuit of dramatically more efficient AI inference with the logarithmic number system.

In this podcast, Sally chats with Lightmatter CEO Nick Harris. As copper reaches its physical limits, Harris explains why photonics is moving from niche technology to AI infrastructure necessity, and why Lightmatter is expanding from optical interconnects into lasers to build the next generation of AI systems.

In this podcast, Lemurian Labs CEO Jay Dawani explains why system-level compilation, not faster chips alone, may determine the future of AI infrastructure.

What if hardware adapted itself to your code instead of forcing developers to optimize for the hardware? In this episode of AI with Sally, Sally Ward-Foxton speaks with NextSilicon CEO Elad Raz about the company’s radically different approach to compute architecture: a runtime-reconfigurable processor designed to optimize itself while applications are running.

Today, on Embedded Edge with Nitin, we’ll explore how advances in touch-based HMI can help optimize the form factor of smart glasses. Our guest is Viveesh Bharathan, Director of Product Marketing at Infineon Technologies. Viveesh specializes in touch HMI, a key technology that shapes how users interact with and experience smart glasses.

In this episode, we’ll examine why touch interfaces play such a pivotal role in smart glasses design, what is changing in the underlying technology, and how these developments can enable slimmer, more practical form factors.

After years of hype, RISC-V is hitting a moment of truth. In 2025 we’ve moved from experimentation to execution – we’ve seen big players make some bold acquisitions, while startups on the scene have been facing commercial realities.

The question is really shifting from “What is RISC-V?” to “Who can actually make it work?” In this episode, we explore what’s driving that transition to execution, and what it means for AI applications.

In this episode, Sally chats with Sakya Dasgupta, CEO of EdgeCortix, about the company’s reconfigurable dataflow architecture, their success in hard applications like space and aerospace, and what’s coming in EdgeCortix’ third generation hardware

In this episode, Sally sits down with analyst Jim McGregor at Nvidia’s GTC to talk about some of the biggest announcements from the show, including Groq, SpectrumX, NemoClaw, and more.

In this episode of AI With Sally, hosted by EE Times’ Sally Ward-Foxton, Muneyb Minhazuddin discusses Ambarella's evolving go-to-market strategy, emphasizing the shift from a direct sales approach to a more collaborative model involving ISVs and system integrators. He highlights the role of AI in creating new market opportunities and the importance of simplifying application development through the DevZone and Agentic Blueprints. The discussion also covers the challenges and strategies in building partnerships, understanding value realization in vertical markets, and the anticipated impact of these changes on Ambarella's growth and market presence.

In this episode, Sally finds out more about Efficient Computer’s reconfigurable spatial dataflow fabric, and how the company is applying it in a very low power edge chip. Brandon Lucia, CEO of Efficient, said the Electron E1 can reconfigure itself for CPU, DSP, or AI workloads, and be performant for all. 

In this podcast conversation, Sally chats with D-Matrix CEO Sid Sheth about test time scaling and what it means for the world of AI hardware.

Today's interview is brought to you by our partner, SiFive. We’re excited to have John Simpson, Senior Principal Architect at SiFive, as our guest. John is involved with the intelligence product line, which centers around RISC-V processor designs aimed at handling AI workloads for applications that span from edge devices to data centers.

In today’s episode, brought to you by Synaptics, we’re diving into a transformative change in Edge AI: the shift towards open, community-focused compiler technology. Synaptics, a frontrunner in embedded chip innovation, is taking a significant step by making its compiler toolchain open-source and encouraging developers around the globe to participate in shaping the future of on-device intelligence, in partnership with Google. Joining us is Dave Garrett, a pivotal figure in this initiative. We’ll discuss the motivations behind this decision, how we align models with hardware, the challenges of solely targeting peak performance metrics, and what implications this holds for developers, the Edge ecosystem, and the future of AI on devices.

In this session, we’ll explore how Infineon’s PSOC Edge is revolutionizing natural language processing (NLP) directly within ultra-low power embedded systems. With cutting-edge advancements in on-device AI acceleration, optimized memory hierarchies, and secure compute domains, PSOC Edge is enabling voice and language understanding at endpoints that previously relied on cloud inference. This breakthrough technology is driving real-time NLP with minimal latency and power consumption, all while ensuring data privacy at the edge.

Joining us today is Omar Cruz from Infineon Technologies, who will unpack the technical innovations and system-side strategies behind this new generation of edge intelligence devices. Together, we’ll dive into how hardware-software co-design is enabling smarter, faster, and more secure speech interfaces for edge devices.

AI training courses are scaling to hundreds of thousands of GPUs and beyond, and the network is under pressure like never before. In this episode, Sally will speak with Don Barnetson,  SVP of Product at Credo Semiconductor, about how reliability is crucial, given that crashing a training run can cost millions of dollars. Credo has spent nearly two decades developing some of the industry’s fastest SERDES and building active electrical cables or AECs to keep AI infrastructure running at peak performance. In this conversation, we’ll dig into the networking reliability issues that come with scaling AI, why reliability matters as much as bandwidth, and how Credo is taking on this problem with copper.

Smart homes and smart, connected devices have been a topic of discussion for over a decade. In this podcast, we will discuss five key disruptive trends that are coming your way in the next 2-4 years that will allow you to interact more intelligently with your smart home while enabling new use cases in home appliances and secured devices.   

Sally Ward Foxton interviews Vishal Sarin, CEO & Founder of Sagence AI.

In this podcast, MIPS CEO Sameer Wasson tells Sally Ward-Foxton that while the IP company is moving towards compute subsystems and custom ASIC tools, it will not become a silicon company.

Optical I/O company Ayar Labs is 10 years old this month. In this podcast, Sally speaks to Ayar CEO Mark Wade about how the company started and where it is headed.

Today, we’re diving into the critical role of network-on-chip (NoC) design in modern system-on-chip (SoC) architectures. Designing efficient interconnects has become a major challenge as SoCs grow more complex, especially with the increasing integration of AI workloads. NoCs now account for a significant portion of silicon area, making it essential to get them right. Michal Siwinski, Chief Marketing Officer at Arteris, will join us in discussing how their FlexNoC tool is revolutionizing NoC design through automation. We’ll explore why this is crucial for today’s chips, how it addresses the growing demands of AI, and what the future holds for NoC technology. 

In this podcast, Sally chats with Arm’s chief architect Richard Grisenthwaite about how AI is changing the security landscape, and whether AI is both a threat and a solution to security issues.

Welcome to another episode of AI with Sally, an EE Times podcast that brings you inside my conversations with luminaries in the AI chip industry. Today’s episode is brought to you by our sponsor, Anaflash. Silicon Valley startup Anaflash announced that it acquired another startup, Legato Logic, a few weeks ago. Anaflash uses nonvolatile memory for its computer memory based AI microcontroller chip and its IP offerings

Welcome to another episode of AI with Sally, an EE Times podcast that brings you inside my conversations with luminaries of the AI chip industry. Today’s episode is brought to you by our sponsor, Infineon Technologies. 

Welcome to a brand new season of AI with Sally, an EE Times podcast that brings you inside my conversations with luminaries of the AI chip industry. Today’s episode is brought to you by our sponsor, Synaptics. Synaptics has recently partnered with Google to add an open-source AI accelerator core that Google developed to Synaptics' next generation of its Astra line of IoT chips. 

In this episode, Sally Ward Foxton sits down with 4DS' Chief Strategy Officer, Peter Himes, to discuss their ReRAM technology referred to as the memory that breathes.

In this podcast, Sally talks to Lemurian Labs CEO Jay Dawani about closing the gap between supply and demand for AI compute using hardware, software and model efficiencies. 

In this podcast, Sally chats with SensiML CEO Chris Rogers about the state of TinyML today and the company’s decision to open source a big chunk of its TinyML toolchain.

In this podcast, Sally chats with Untether’s Bob Beachler about the company’s automotive roadmap, the demand for AI in automotive, AI workloads in the car and the dawn of automotive chiplets. 

In this episode, Sally chats with Sima.ai CEO Krishna Rangasayee about the company’s software-centric approach, the company’s SoC with homegrown AI accelerator, and why they rely on Arm cores ahead of RISC-V.

In this podcast, Sally talks to Winbond’s Omar Ma to find out about CUBE, the company’s 3D-packaged memory concept that puts the memory die in the middle of the sandwich, rather than on top.

In this podcast, Sally interviews BrainChip CMO Nandan Nayampally about the company's second-generation architecture for spiking neural network acceleration, which now includes hardware support for transformer networks like ViT.

In this podcast, Sally chats to Qualcomm's Vinesh Sukumar about the company's demos of generative AI running on Snapdragon mobile phone processors and the future of generative AI at the edge, as well as some of the tricks up Snapdragon's sleeve for AI acceleration.

In this podcast, Sally speaks to SambaNova CEO Rodrigo Liang about how the success of ChatGPT and other LLMs is impacting businesses, what this means for compute democratization and open-source approaches, and how big LLMs can get. 

In this podcast episode , Sally speaks to SynSense’s Dylan Muir about the company’s design win for its neuromorphic processor in a toy robot that recognises gestures, the company’s two processors and the differences between them, as well as the synergies between dynamic vision sensor cameras and neuromorphic processors.

In this podcast, Sally speaks to Silicon Labs' Matt Maupin and Dan Kozin about the company's wireless IoT chips with AI acceleration, what use cases need this capability, how the accelerator fits into the device's deep sleep modes, and how AI works with the company's software stack. 

In this episode, Sally speaks with NXP’s director of AI, Ali Ors, about the decision to move to in-house IP for NPUs in NXP’s microcontroller and application processor lines. We also discuss NXP’s NPU roadmap, software stack, and new AI model watermarking feature.

Artificial Intelligence: In this pilot episode of the AI podcast, we ask: Why is recognising sounds so hard? Could we build an artificial brain out of chips? And what has Graphcore been up to lately?