Led the design and development of a purpose-built LLM inference engine to provide generative AI inference workloads powered by IBM AIU NorthPole hardware to define the state-of-the-art.
Demonstrated rack-scale distributed AI system deployments of 288 NorthPole cards, capable of collectively producing over 500,000 generated tokens-per-second whilst simultaneously maintaining model-optimal individual per-token latencies as low as 1 millisecond.
Designed, developed, and deployed a cloud-native stack on OpenShift/Kubernetes to expose and control access to IBM AIU NorthPole powered LLM AI inference appliances. Worked with engineers to integrate the services into the IBM watsonx product to enable IBM AIU NorthPole-accelerated LLM inference workloads across the platform.
Performed role of primary maintainer of open-source C/C++ project for massively parallel simulation of high performance computing (HPC) communication networks known as CODES. Collaborated with researchers from institutions including Argonne and Sandia National Laboratories.
Participated as a steering-committee member on an NSF funded project-of-projects and acted as a subject-matter-expert and mentor in the areas of high performance computing and AI systems for participating graduate students.
Employment Experience
IBM Research. Staff Research Scientist: October 2022 - July 2026
Team lead role driving development of the runtime stack and SDK packaging/release process for the IBM AIU NorthPole accelerator card: a brain-inspired computing hardware device for state-of-the-art AI inference capable of simultaneously providing increased performance at significantly reduced energy usage than comparable GPUs and other neural accelerator devices.
Subject matter expert in parallel and distributed computing systems, containerization and orchestration, and the serving of LLM inference systems.
Technical representative for IBM AIU NorthPole during international business development and client outreach events and meetings.
Developed and maintained a cloud-native stack on OpenShift/Kubernetes for scalable LLM AI inference, integrated into production IBM watsonx platform workloads as a research-preview service. This effort showcased rack-scale distributed AI network deployments of hundreds of NorthPole cards distributed across many networked hosts.
Developed a purpose-built, bespoke, LLM inference engine stack to provide generative AI workload capabilities powered by NorthPole hardware to obtain bleeding-edge latency and throughput performance metrics.
Rensselaer Polytechnic Institute. Research Scientist: July 2021 - September 2022
Center for Compuational Innovations
Led complex scientific and technical efforts at the Center for Computational Innovations, focusing on software development and benchmarks in High Performance Computing (HPC) environments.
External collaborator on research projects for the IBM AI Hardware Center involving distributed AI training benchmarking and simulation of composable systems.
Provided technical expertise to enhance design, implementation, and analysis of research procedures.
Identified and pursued funding opportunities to support innovative research projects in collaboration with the center director.
Provided technical expertise to enhance design, implementation, and analysis of research.
Triaged and prioritized center needs for research facilitation of thousands of users across multiple supercomputer systems.
Rensselaer Polytechnic Institute. Software Engineer: February 2020 - June 2021
Center for Compuational Innovations
Conducted research and development of software for simulating High Performance Computing (HPC) interconnection networks.
Collaborated with external research partners to tailor software solutions for specific project requirements.
Generated relevant research data to support the Center for Computational Innovations at Rensselaer Polytechnic Institute.
Contributed to the research and development of firmware for Cisco Meraki's MR Platform.
Designed and developed a lockless thread-safe hashtable utilizing RCU techniques. Contributions submitted to open-source software-defined router project: Click Modular Router.
Rensselaer Polytechnic Institute. Research Assistant: Fall 2014 - June 2021
Advisor: Christopher Carothers
Active member of the Department of Energy's Exascale Compute Project (ECP), developing and evaluating models of prototypical exascale supercomputer communication network designs through simulation.
Maintainer of CODES HPC network/storage simulation framework built on top of the ROSS parallel discrete event simulation (PDES) environment.
Fufilled duties as a research assistant with the SuperNeuro research group, developing models for simulation of neurmorphic systems and associated software.
Primary area of research: High Performance/Parallel Computing
Other areas of interest: Distributed Computing, Machine Learning
Rensselaer Polytechnic Institute. Teaching Assistant - Computer Science 1: Fall 2014
Professor: Sibel Adali
Support to professor during course teaching fundamentals of computer science using Python.
Facilitated laboratory classes and discussions, hosted office hours, graded homework and exams.
University of Oklahoma. Research Assistant: May 2012 -- May 2014
Advisor: Sheena Murphy
Continued REU research, performing a closer inspection of electrical transport properties of antimony measured at cold temperatures, including first-observations of weak anti-localization in quantum confined films.
Worked on developing and refining a method for measuring differential conductance of a material, allowing for a greater understanding of the interface between a topological insulator and a superconductor.
University of Oklahoma. National Science Foundation REU: Summer 2012, 2013
Advisor: Sheena Murphy
Participated in condensed matter physics research and analysis under an NSF Materials Research Science and Engineering Center (MRSEC) grant from advisor.
Worked alongside graduate students in a laboratory environment.
Performed data collection, statistical interpretation of collected data, and utilized software associated with analysis of collected data (Mathematica, LabVIEW).
Participated in metal workshop course to qualify for use of the student shop in fabricating parts for laboratory equipment.
Michael V. DeBole, Rathinakumar Appuswamy, Neil McGlohon, Brian Taba, Steven K. Esser, Filipp Akopyan, John V. Arthur, Arnon Amir, Alexander Andreopoulos, Peter J. Carlson, Andrew S. Cassidy, Pallab Datta, Myron D. Flickner, Rajamohan Gandhasri, Guillaume J. Garreau, Megumi Ito, Jennifer L. Klamo, Jeffrey A. Kusnitz, Nathaniel J. McClatchey, Jeffrey L. McKinstry, Tapan K. Nayak, Carlos Ortega Otero, Hartmut Penner, William P. Risk, Jun Sawada, Jay Sivagnaname, Daniel F. Smith, Rafael Sousa, Ignacio Terrizzano, Takanori Ueda, Trent Gray-Donald, David Cox, and Dharmendra S. Modha.
ArXiV 2511.15950v1, November 2025 -- Preprint Article (Preprint Link) (Local Link)
Rathinakumar Appuswamy, Michael DeBole, Brian Taba, Steve Esser, Andrew Cassidy, Arnon Amir, Alexander Andreopoulos, Deepika Bablani, Pallab Datta, Jeff Kusnitz, Nathaniel McClatchey, Neil McGlohon, Jeffrey McKinstry, Tapan Kumar Nayak, Daniel F. Smith, Rafael Cardoso Fernandes Sousa, Ignacio Terrizzano, Filipp Akopyan, Peter Carlson, Rajamohan Gandhasri, Guillaume Garreau, Nelson Mimura Gonzalez, Megumi Ito, Jennifer Klamo, Yutaka Nakamura, Carlos Tadeo Ortega Otero, William Risk, Jun Sawada, Kai Schleupen, Jay Sivagnaname, Matthew Stallone, Takanori Ueda, Myron Flickner, John Arthur, Rameswar Panda, David Cox, and Dharmendra Modha.
IEEE High Performance Extreme Computing (HPEC), September 2024, Boston, USA. (Preprint Link) (Local Link)
Filipp Akopyan, William Risk, John Arthur, Andrew Cassidy, Michael DeBole, Carlos Tadeo Ortega Otero, Jun Sawada, Evan Colgan, Michael Criscolo, Phillip Mann, Heinz Baier, Kai Schleupen, Arnon Amir, Alexander Andreopoulos, Rathinakumar Appuswamy, Deepika Bablani, Peter Carlson, Pallab Datta, Steve Esser, Myron Flickner, Rajamohan Gandhasri, Guillaume Garreau, Megumi Ito, Jennifer Klamo, Jeff Kusnitz, Nathaniel McClatchey, Neil McGlohon, Jeffrey McKinstry, Yutaka Nakamura, Tapan Kumar Nayak, Jay Sivagnaname, Daniel Smith, Rafael Cardoso Fernandes Sousa, Brian Taba, Ignacio Terrizzano, Takanori Ueda, and Dharmendra Modha.
IEEE High Performance Extreme Computing (HPEC), September 2024, Boston, USA. (Preprint Link) (Local Link)
Elkin Cruz-Camacho, Siyuan Qian, Ankit Shukla, Neil McGlohon, Shaloo Rakheja and Christopher D. Carothers.
ACM Transactions on Modeling and Computer Simulation (TOMACS), March 2024. (Official Link) (Local Link)
Elkin Cruz-Camacho, Siyuan Qian, Ankit Shukla, Neil McGlohon, Shaloo Rakheja and Christopher D. Carothers.
ACM SIGSIM Conference on Principles of Advanced Discrete Simulation (PADS), June 2022. Virtual (Official Link) (Local Link)
Neil McGlohon, K. Scott Hemmert, Kevin A. Brown, Michael Levenhagen, Sudheer Chunduri, Robert B. Ross, Christopher D. Carothers.
IEEE SC21 Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems, November 2021. Virtual (Official Link) (Local Link)
Julie Ma, John Goodhue, Kaylea Nelson, Andrew Sherman, Eric Brown, Christopher Carothers, Galen Collier, Adrian Del Maestro, Andrea Elledge, Wayne Figurelle, John Huffman, Gaurav Khanna, Neil McGlohon, Sia Najafi, Jeff Nucciarone, Anita Schwartz, Bruce Segee, Scott Valcourt and Ralph Zottola.
PEARC Workshop on Strategies for Enhancing HPC Education and Training (SEHET), July 2021. Virtual (Official Link) (Local Link)
Neil McGlohon and Christopher D. Carothers.
ACM SIGSIM Winter Simulation Conference (WSC), December 2021. Virtual -- Advanced Tutorial Paper (Official Link) (Local Link)
Kevin A. Brown, Neil McGlohon, Sudheer Chunduri, Robert B. Ross, Eric Borch, Christopher D. Carothers, and Kevin Harms.
ISC High Performance (ISC), June 2021. Virtual (Official Link) (Local Link)
Neil McGlohon, Robert B. Ross, and Christopher D. Carothers.
ACM SIGSIM Conference on Principles of Advanced Discrete Simulation (PADS), June 2020. Virtual (Official Link) (Local Link)
Neil McGlohon, Noah Wolfe, Misbah Mubarak, and Christopher D. Carothers.
ACM SIGSIM Conference on Principles of Advanced Discrete Simulation (PADS), June 2019. Chicago, USA (Official Link) (Local Link)
Yao Kang, Xin Wang, Neil McGlohon, Misbah Mubarak, Sudheer Chunduri, and Zhiling Lan.
ACM SIGSIM Conference on Principles of Advanced Discrete Simulation (PADS), June 2019. Chicago, USA (Official Link) (Local Link)
Misbah Mubarak, Neil McGlohon, Malek Musleh, Eric Borch, Robert B. Ross, Ram Huggahalli, Sudheer Chunduri, Scott Parker, Christopher D. Carothers, and Kalyan Kumaran.
ISC High Performance (ISC), June 2019. Frankfurt, Germany (Official Link) (Local Link)
Mark Plagge, Christopher D. Carothers, Elsa Gonsiorowski, and Neil McGlohon.
ACM Transactions on Modeling and Computer Simulation (TOMACS), September 2018 (Official Link) (Local Link)
Mark Plagge, Neil McGlohon, Caitlin Ross, and Christopher D. Carothers.
Neuromorphic Computing Symposium on Architectures, Models, and Applicaitons, July 2017. Oak Ridge, USA -- Extended Abstract/Presentation
S. Cairns, N. McGlohon, C. Robison, J. Keay, C. K. Gaspe, K. S. Wickramasinghe, T. D. Mishima, M. B. Santos, S. Q. Murphy
American Physical Society, APS March Meeting, March 2013. Baltimore, Maryland -- Extended Abstract/Presentation
Other Experience
Academic Service
Committee Work
2025 -- ACM SIGSIM Principles of Advanced Discrete Simulation (PADS) - Program Committee Member
2024 -- ACM SIGSIM Principles of Advanced Discrete Simulation (PADS) - Program Committee Member
2023 -- ACM SIGSIM Principles of Advanced Discrete Simulation (PADS) - Program Committee Member
2022 -- ACM SIGPLAN Benchmarking in the Data Center: Expanding to the Cloud (BID) - Program Committee Member
2022 -- IEEE IPDPS Workshop on Scalable Deep Learning over Parallel and Distributed Infrastructure (ScaDL) - Program Committee Member
2020-2022 -- NSF CAREERS Cyberteam Program - Steering Committee Member
Peer-Reviewer
2024 -- ACM SIGSIM Principles of Advanced Discrete Simulation (PADS'24)
2023 -- ACM SIGSIM Principles of Advanced Discrete Simulation (PADS'23)
2023 -- IEEE IPDPS Workshop on Scalable Deep Learning over Parallel and Distributed Infrastructure (ScaDL)
2022 -- ACM SIGPLAN Benchmarking in the Data Center: Expanding to the Cloud (BID)
2022 -- IEEE IPDPS Workshop on Scalable Deep Learning over Parallel and Distributed Infrastructure (ScaDL)
2021 -- IEEE Transactions on Parallel and Distributed Systems (TPDS)
2021 -- IEEE European Control Conference (ECC'21)
2020 -- IEEE Transactions on Parallel and Distributed Systems (TPDS)
2019 -- ACM SIGSIM Principles of Advanced Discrete Simulation (PADS'19)
Senior Capstone Research Project
The final year of undergraduate work in the physics department of the University of Oklahoma was spent participating in a final research project overseen by faculty members Sheena Murphy and Matthew Johnson. Continued on work performed over my two summer REUs and other research conducted during the school terms. Presentations were given and critiqued by advisors and students over the course of the project.
The Oklahoma Daily, The University of Oklahoma. Editor of Photography, Photographer: Aug 2009 -- May 2011
Participated as active member of editorial board for the newspaper. Managed staff of photographers, utilized time management and decision making to meet firm deadlines.
Science Museum Oklahoma. Oklahoma City, OK. Educator June 2006 -- May 2011
Conducted and developed teaching material for live science presentations. Helped staff overnight events, which included facilitating science-based projects for children and their parents.
