| Page 205 | Kisaco Research
Memory
Generative AI

Author:

Euicheol Lim

Research Fellow, System Architect
SK Hynix

Eui-cheol Lim is a Research Fellow and leader of Solution Advanced Technology team in SK Hynix. He received the B.S. degree and the M.S. degree from Yonsei University, Seoul, Korea, in 1993 and 1995, and the Ph.D. degree from Sungkyunkwan University, suwon, Korea in 2006. Dr.Lim joined SK Hynix in 2016 as a system architect in memory system R&D. Before joining SK Hynix, he had been working as an SoC architect in Samsung Electronics and leading the architecture of most Exynos mobile SoC. His recent interesting points are memory and storage system architecture with new media memory and new memory solution such as CXL memory and Processing in Memory. In particular, he is proposing a new computing architecture based on PIM, which is more efficient and flexible than existing AI accelerators, to process generative AI and LLM (large language Model) that is currently causing a sensation.

Euicheol Lim

Research Fellow, System Architect
SK Hynix

Eui-cheol Lim is a Research Fellow and leader of Solution Advanced Technology team in SK Hynix. He received the B.S. degree and the M.S. degree from Yonsei University, Seoul, Korea, in 1993 and 1995, and the Ph.D. degree from Sungkyunkwan University, suwon, Korea in 2006. Dr.Lim joined SK Hynix in 2016 as a system architect in memory system R&D. Before joining SK Hynix, he had been working as an SoC architect in Samsung Electronics and leading the architecture of most Exynos mobile SoC. His recent interesting points are memory and storage system architecture with new media memory and new memory solution such as CXL memory and Processing in Memory. In particular, he is proposing a new computing architecture based on PIM, which is more efficient and flexible than existing AI accelerators, to process generative AI and LLM (large language Model) that is currently causing a sensation.

Author:

Mark Kuemerle

VP, Technology, Custom Cloud Solutions
Marvell

Mark Kuemerle is Vice President, Technology, Custom Cloud Solutions at Marvell. In this role, Mark is responsible for defining leading-edge ASIC offerings, drives product competitiveness, and architects system-level solutions. Before joining Marvell, Mark was a Fellow in Integrated Systems Architecture at GLOBALFOUNDRIES and has held multiple engineering positions at IBM.   

He has authored numerous articles on die-to-die connectivity and multichip systems and holds several patents related to low-power technologies and package integration. Mark earned a Master of Science and a Bachelor of Science degree in Computer Engineering from Case Western Reserve University. 

 

Mark Kuemerle

VP, Technology, Custom Cloud Solutions
Marvell

Mark Kuemerle is Vice President, Technology, Custom Cloud Solutions at Marvell. In this role, Mark is responsible for defining leading-edge ASIC offerings, drives product competitiveness, and architects system-level solutions. Before joining Marvell, Mark was a Fellow in Integrated Systems Architecture at GLOBALFOUNDRIES and has held multiple engineering positions at IBM.   

He has authored numerous articles on die-to-die connectivity and multichip systems and holds several patents related to low-power technologies and package integration. Mark earned a Master of Science and a Bachelor of Science degree in Computer Engineering from Case Western Reserve University. 

 

Memory

Author:

Rochan Sankar

Co-Founder & CEO
Enfabrica

Rochan is Founder, President and CEO of Enfabrica. Prior to founding Enfabrica, he was Senior Director and leader of the Data Center Ethernet switch silicon business at Broadcom, where he defined and brought to market multiple generations of Tomahawk/Trident chips and helped build industry-wide ecosystems including 25G Ethernet and disaggregated whitebox networking.

Prior, he held roles in product management, chip architecture, and applications engineering across startup and public semiconductor companies. Rochan holds a B.A.Sc. in Electrical Engineering from the University of Toronto and an MBA from the Wharton School, and has 6 issued patents.

Rochan Sankar

Co-Founder & CEO
Enfabrica

Rochan is Founder, President and CEO of Enfabrica. Prior to founding Enfabrica, he was Senior Director and leader of the Data Center Ethernet switch silicon business at Broadcom, where he defined and brought to market multiple generations of Tomahawk/Trident chips and helped build industry-wide ecosystems including 25G Ethernet and disaggregated whitebox networking.

Prior, he held roles in product management, chip architecture, and applications engineering across startup and public semiconductor companies. Rochan holds a B.A.Sc. in Electrical Engineering from the University of Toronto and an MBA from the Wharton School, and has 6 issued patents.

Author:

Anahita Mouro

Global Lead, Data Center Field Reliability & Quality
Google

Transformational Quality Leader with over 15 years of experience in mission-critical industries and technical infrastructure with a proven track record in driving operational excellence and product reliability and quality improvements through innovative strategies, exceptional leadership, and meticulous execution.  She is adept at enhancing organizational efficiency, reducing costs, and fostering a culture of continuous improvement. Anahita is a certified ASQ Six Sigma Black Belt and Quality Engineer with deep expertise in managing large-scale projects and leading cross-functional teams to achieve strategic goals.
Passionate about building and leading high-performing technical teams and enable their success and growth.

Anahita Mouro

Global Lead, Data Center Field Reliability & Quality
Google

Transformational Quality Leader with over 15 years of experience in mission-critical industries and technical infrastructure with a proven track record in driving operational excellence and product reliability and quality improvements through innovative strategies, exceptional leadership, and meticulous execution.  She is adept at enhancing organizational efficiency, reducing costs, and fostering a culture of continuous improvement. Anahita is a certified ASQ Six Sigma Black Belt and Quality Engineer with deep expertise in managing large-scale projects and leading cross-functional teams to achieve strategic goals.
Passionate about building and leading high-performing technical teams and enable their success and growth.

Running workloads on the edge means operating with a finite amount of compute resources, which means that running workloads as lightweight as possible is generally preferable. In contrast, securely operating workloads in the cloud often means spinning up additional virtual machines for strong workload isolation. On the edge, this strategy is often not feasible. This talk covers how you can securely run containers in lightweight Kubernetes clusters on the edge entirely without the need for virtualization. This talk will cover different hardening approaches and compare them with special focus on securing AI workloads on the edge.

Autonomy
On-Device ML
Compute
Industrial Edge

Author:

Lukas Gentele

CEO
vCluster Labs

Lukas Gentele is the CEO & Co-Founder of vCluster Labs, a venture-backed startup virtualizing Kubernetes to enable advanced tenancy models to increase utilization, reduce cost and make Kubernetes more dynamic than ever. vCluster enables platform and infra teams to create virtual Kubernetes clusters which are as scalable and isolated as traditional clusters but much more lightweight and versatile. Trusted by companies such as CoreWeave, Nscale, Adobe, and Deloitte, vCluster enables organizations to create fully isolated tenant clusters on any infrastructure, from public cloud to private clouds all the way to AI supercomputers powered by the latest GPUs. Lukas has been a keynote speaker and presenter at events such as KubeCon, DevOpsDays, ContainerConf, as well as at AWS and Kubernetes Community Days around the world.

Lukas Gentele

CEO
vCluster Labs

Lukas Gentele is the CEO & Co-Founder of vCluster Labs, a venture-backed startup virtualizing Kubernetes to enable advanced tenancy models to increase utilization, reduce cost and make Kubernetes more dynamic than ever. vCluster enables platform and infra teams to create virtual Kubernetes clusters which are as scalable and isolated as traditional clusters but much more lightweight and versatile. Trusted by companies such as CoreWeave, Nscale, Adobe, and Deloitte, vCluster enables organizations to create fully isolated tenant clusters on any infrastructure, from public cloud to private clouds all the way to AI supercomputers powered by the latest GPUs. Lukas has been a keynote speaker and presenter at events such as KubeCon, DevOpsDays, ContainerConf, as well as at AWS and Kubernetes Community Days around the world.

Data Privacy & Governance

Author:

Rohith Vangalla

Lead Software Engineer
Optum

Dr. Rohith Vangalla is a Senior IEEE Member, AI Researcher, and Lead Software Engineer at Optum Technologies, specializing in AI-driven automation, cybersecurity, and enterprise AI infrastructure. With over ten years of experience, he has pioneered AI solutions in healthcare, digital marketing, and aviation, publishing impactful research that has transformed industry practices. At Optum, he has been instrumental in developing AI-driven chatbots, secure automation frameworks, and scalable AI solutions that enhance efficiency, compliance, and real-time decision-making. As a scholar, reviewer, and judge for major AI conferences, Dr. Vangalla continues to shape the future of AI infrastructure, privacy-first systems, and responsible AI development.

Rohith Vangalla

Lead Software Engineer
Optum

Dr. Rohith Vangalla is a Senior IEEE Member, AI Researcher, and Lead Software Engineer at Optum Technologies, specializing in AI-driven automation, cybersecurity, and enterprise AI infrastructure. With over ten years of experience, he has pioneered AI solutions in healthcare, digital marketing, and aviation, publishing impactful research that has transformed industry practices. At Optum, he has been instrumental in developing AI-driven chatbots, secure automation frameworks, and scalable AI solutions that enhance efficiency, compliance, and real-time decision-making. As a scholar, reviewer, and judge for major AI conferences, Dr. Vangalla continues to shape the future of AI infrastructure, privacy-first systems, and responsible AI development.

Networking

Author:

Vladimir Stonjanvic

CTO & Co-founder
Ayar Labs

Vladimir is the Chief Technology Officer of Ayar Labs. Prior to founding Ayar Labs, he led the team that designed the world’s first processor to communicate using light. Vladimir was recently a professor of EECS at UC Berkeley, and was one of the key developers of the Rambus high-speed link technology. He holds a PhD from Stanford University.

Vladimir Stonjanvic

CTO & Co-founder
Ayar Labs

Vladimir is the Chief Technology Officer of Ayar Labs. Prior to founding Ayar Labs, he led the team that designed the world’s first processor to communicate using light. Vladimir was recently a professor of EECS at UC Berkeley, and was one of the key developers of the Rambus high-speed link technology. He holds a PhD from Stanford University.

Panelists

Author:

Erick Dela Pena

Director, Sales Engineering
Coresite

Erick Dela Pena

Director, Sales Engineering
Coresite

Author:

Taymur Ahmad

Founder & CEO
actnano

Taymur Ahmad is the Founder and CEO of actnano Inc. Prior to founding actnano, Mr. Ahmad had 18 years of manufacturing management experience with Fortune 50 companies such as Alcoa and Philips Electronics. Among other accolades, in 2010 he was awarded the "Visionary of the Year" award by Surface Mount Technology magazine. Mr. Ahmad's success stories have been featured in various magazines and newspapers including USA Today. Dell's Center for Entrepreneurs picked Mr. Ahmad to be one of the top 50 CEO's in the world. He is a member of the Dell founders 50 club and the Philips Alumni Club. Mr. Ahmad speaks 5 languages, and has lived in Europe and Asia. He earned his MBA from Business School Lausanne in Switzerland, and his Engineering degree from the University of Iowa.

Taymur Ahmad

Founder & CEO
actnano

Taymur Ahmad is the Founder and CEO of actnano Inc. Prior to founding actnano, Mr. Ahmad had 18 years of manufacturing management experience with Fortune 50 companies such as Alcoa and Philips Electronics. Among other accolades, in 2010 he was awarded the "Visionary of the Year" award by Surface Mount Technology magazine. Mr. Ahmad's success stories have been featured in various magazines and newspapers including USA Today. Dell's Center for Entrepreneurs picked Mr. Ahmad to be one of the top 50 CEO's in the world. He is a member of the Dell founders 50 club and the Philips Alumni Club. Mr. Ahmad speaks 5 languages, and has lived in Europe and Asia. He earned his MBA from Business School Lausanne in Switzerland, and his Engineering degree from the University of Iowa.

Author:

Harsha Bojja

Principal AI Platform Architect
Microsoft

Harsha Bojja serves as a Principal AI Platform Architect at Microsoft, where he leads the design and development of AI systems and infrastructure. His expertise spans system performance optimization, availability modeling, and thermal management—critical for supporting large-scale training and inference clusters. Harsha’s career includes pivotal roles in AI/ML infrastructure and product development. His experience at Meta Platforms, Bell Labs, and cloud infrastructure startups has equipped him with deep technical insight and strategic vision. He is a Senior Member of IEEE, serves on the Industrial Advisory Board, and contributes to the OCP Rack and Power Steering Committee. Harsha has authored papers presented at IEEE, ASME, and ACEEE conferences, and actively contributes to the Open Compute Project community, reflecting his commitment to advancing scalable and secure AI infrastructure.

Harsha Bojja

Principal AI Platform Architect
Microsoft

Harsha Bojja serves as a Principal AI Platform Architect at Microsoft, where he leads the design and development of AI systems and infrastructure. His expertise spans system performance optimization, availability modeling, and thermal management—critical for supporting large-scale training and inference clusters. Harsha’s career includes pivotal roles in AI/ML infrastructure and product development. His experience at Meta Platforms, Bell Labs, and cloud infrastructure startups has equipped him with deep technical insight and strategic vision. He is a Senior Member of IEEE, serves on the Industrial Advisory Board, and contributes to the OCP Rack and Power Steering Committee. Harsha has authored papers presented at IEEE, ASME, and ACEEE conferences, and actively contributes to the Open Compute Project community, reflecting his commitment to advancing scalable and secure AI infrastructure.