People
People in inference and serving
89 people in the USASI People directory whose profiles list inference and serving as a field of their work. Listed alphabetically; this is not a ranking. Each profile covers public professional work only, cited to official pages.
0xSero
Developer; the Omacom Foundation's announcement names Sybil Solutions as 0xSero's company, Sybil Solutions
Developer of the Local AI Registry, tested recipes for running open models on specific GPUs
Aaron Teo
Technology Engineer, IBM Client Engineering, IBM
IBM technology engineer and code owner for llama.cpp's zDNN backend for IBM Z and LinuxONE
Adrien Gallouët
Hugging Face is the company listed on Gallouët's GitHub profile, Hugging Face
Member of llama.cpp's llama-server and shared-code code-owner teams; Hugging Face
Akshat Bubna
Co-founder and CTO, Modal
Co-founder and CTO of Modal, the serverless cloud platform for AI and data workloads
Aldehir Rojas
Member of the llama-common code-owner team, llama.cpp project
llama.cpp shared-code owner working on chat parsing, tool calls and JSON-schema grammars
Amir Haghighat
Co-founder and Chief Technology Officer, Baseten
Co-founder and CTO of Baseten, the AI inference platform
Andrew Feldman
Chief Executive Officer and Co-Founder, Cerebras Systems
Co-founder and Chief Executive Officer of Cerebras Systems; earlier co-founder and CEO of SeaMicro
Arjun Desai
Co-founder, Cartesia
Co-founder of Cartesia; co-author of Llamba, distilled recurrent language models
Awni Hannun
Member of the Technical Staff, Anthropic
Co-creator of MLX, an array framework for machine learning on Apple silicon
Azalia Mirhoseini
Assistant Professor of Computer Science; directs the Scaling Intelligence lab, Stanford University
Stanford assistant professor directing Scaling Intelligence; co-founder of Ricursive Intelligence
Bartowski
Senior Machine Learning Engineer, Red Hat
Publishes GGUF quantizations of open models and contributes to llama.cpp; ML engineer at Red Hat
Bill Dally
Chief scientist and senior vice president of NVIDIA Research, NVIDIA
Chief scientist and SVP of Research at NVIDIA; co-author of Deep Compression; former Stanford CS chair
Byron Hsu
Merge oncall for prefill-decode (PD) disaggregation, SGLang project
Led Liger Kernel, open-source Triton kernels for memory-efficient LLM training and fine-tuning
Carlos Costa
Distinguished Engineer, IBM
IBM Distinguished Engineer and llm-d project lead for inference optimization research
Chris Lattner
Co-founder, Modular
Co-founder of Modular, maker of the MAX inference framework and the Mojo language
Dane Knecht
Chief Technology Officer, Cloudflare
Chief Technology Officer of Cloudflare; led Zero Trust, the Developer Platform and AI inference work
Daniel Bevenius
Hugging Face is the company listed on Bevenius's GitHub profile, Hugging Face
llama.cpp code owner for model-conversion tooling and member of its CI team; Hugging Face
Daniel Han
Listed on Unsloth's About page for software, data, and algorithms, Unsloth
Works on Unsloth, open-source software for fine-tuning and running models on local hardware
Davide Eynard
Open-source and trustworthy AI work (blog author), Mozilla.ai
Mozilla.ai engineer working on open-source AI; author of the llamafile 0.10.0 release post
Dmytro Dzhulgakov
Co-Founder, Fireworks AI
Co-founder of Fireworks AI; previously a PyTorch core maintainer at Meta
Dylan Patel
Author of the SemiAnalysis newsletter, SemiAnalysis
Author of the SemiAnalysis newsletter on the semiconductor and AI supply chain
Eric Hartford
Founder, Quixi.AI
Founder of Quixi.AI and creator of the Dolphin and Samantha open models; formerly at Microsoft and AWS
Erik Bernhardsson
Founder and CEO, Modal
Founder and CEO of Modal; creator of the open-source Annoy library and co-creator of Luigi at Spotify
Erik Gafni
Founder and CTO, TypeSafe AI
Co-founder and CTO of TypeSafe AI; previously founded Ravel, a multimodal AI company for DNA sequencing
Furu Wei
Distinguished Scientist and Vice President; Chief Scientist of Microsoft Research Asia, leading the GenAI group, Microsoft Research
Distinguished Scientist and Chief Scientist of Microsoft Research Asia; senior author of the BitNet papers
Gavin Uberti
Co-founder and CEO, Etched
Co-founder and CEO of Etched, which builds inference chips and racks; former Apache TVM contributor
Georgi Gerganov
Maintains llama.cpp with the ggml team, Hugging Face
Develops llama.cpp and the ggml tensor library for running models on local hardware
Hani Jamjoom
Listed with IBM Research on the 2025 GPU confidential computing paper and with the IBM T.J. Watson Research Center on a 2026 arXiv paper, IBM Research
Systems security researcher listed with IBM Research; co-author of confidential-computing studies for AI
Hao Zhang
Assistant Professor, Halıcıoğlu Data Science Institute and Computer Science and Engineering; leads the Hao AI Lab, University of California San Diego
UC San Diego assistant professor who leads the Hao AI Lab; FastVideo, vLLM and Chatbot Arena co-author
Horace He
Core Maintainer, PyTorch
PyTorch core maintainer and torch.compile contributor; wrote a Thinking Machines post on LLM nondeterminism
Ian Buck
Vice President of Hyperscale and High-Performance Computing, NVIDIA
Vice president of hyperscale and HPC at NVIDIA; described by NVIDIA as the inventor of CUDA
Ion Stoica
Professor of Computer Science, Xu Bao Chancellor Chair; Director of the Sky Computing Lab, University of California, Berkeley
Co-author of the Ray and vLLM papers; UC Berkeley professor and co-founder of Databricks and Anyscale
Jeff Bolz
Distinguished Engineer, NVIDIA
NVIDIA Distinguished Engineer and member of llama.cpp's Vulkan backend code-owner team
Jeff Johnson
Research Scientist, SysML group, Fundamental AI Research (FAIR), Meta
Meta FAIR research scientist; implemented the GPU version of the Faiss similarity search library
Jeffrey Morgan
Building Ollama, Ollama
Works on Ollama, an open-source tool for running open models on your own machine
Johannes Gäßler
Experimental particle physicist, Karlsruhe Institute of Technology
Member of llama.cpp's CUDA backend code-owner team; experimental particle physicist at KIT
Jonathan Ross
Founder; CEO and Founder in 2024 and 2025 announcements, Groq
Founder and former CEO of Groq, maker of the LPU inference chip and the GroqCloud platform
Joseph E. Gonzalez
Associate Professor, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley
UC Berkeley professor whose group built Gorilla and the Berkeley Function Calling Leaderboard
Joshua Lochner
Working on Transformers.js, Hugging Face
Works on Transformers.js at Hugging Face, a library for running Transformers models in the browser
Julien Simon
AI Operating Partner, Fortino Capital
AI Operating Partner at Fortino Capital; former Chief Evangelist at Hugging Face and Arcee AI
Kaichao You
Co-founder and Chief Scientist, Inferact
Lead maintainer of vLLM; co-founder and Chief Scientist of Inferact; creator of depyf
Krithik Puthalath
Founder and CEO, Zyphra
Founder and CEO of Zyphra, the open-model research lab behind Zamba and Zyphra Cloud
Kunle Olukotun
Co-founder and Chief Technologist, SambaNova
Co-founder and Chief Technologist of SambaNova; Cadence Design Professor at Stanford University
Luis Héctor Chávez
Chief Technology Officer, Replit
Chief Technology Officer of Replit, writing on its infrastructure, snapshot engine and platform security
Mark Saroufim
Cofounder, Core Automation
Co-founder of Core Automation and of GPU MODE; PyTorch maintainer whose work includes torchao
Matt Hicks
President and Chief Executive Officer, Red Hat
President and CEO of Red Hat and an IBM Senior Vice President; a founding engineer on the OpenShift team
Matthew Prince
Co-founder and CEO, Cloudflare
Co-founder and CEO of Cloudflare, whose Workers platform runs AI models and applications at the network edge
Matthew Zeiler
Founder and CEO (as described in Nebius's May 2026 announcement), Clarifai
Clarifai founder named SVP, Research at Nebius in May 2026; author of the ADADELTA paper
Matthijs Douze
Research Scientist, Fundamental AI Research (FAIR), since November 2015, Meta
Research scientist at Meta FAIR; implemented most of the CPU side of the Faiss similarity search library
Max Krasnyansky
Member of the Hexagon and OpenCL backend code-owner teams, llama.cpp project
Author of llama.cpp's Hexagon NPU backend; member of its Hexagon and OpenCL code-owner teams
Mia
Developer, Mia's AI Lab
Developer of local model deployment recipes and the sparkDash monitoring dashboard
Michael Intrator
Co-founder, Chairman and Chief Executive Officer (leading the company since 2017), CoreWeave
Co-founder, Chairman and CEO of CoreWeave, a cloud built for AI training and inference
Mitesh Agrawal
Head of Cloud, Lambda
Lambda's Head of Cloud in 2023–2024 posts; introduced Lambda 1-Click Clusters of NVIDIA H100 GPUs
Neo Zhang
Code owner for the SYCL backend (ggml-org/ggml-sycl), llama.cpp project
Code owner for llama.cpp's SYCL backend, which is designed primarily for Intel GPUs
Olivier Chafik
Anthropic is the company listed on Chafik's GitHub profile, Anthropic
MCP TypeScript SDK maintainer; added Jinja chat templates and tool calling to llama.cpp
Pankaj Gupta
Co-founder, Baseten
Co-founder of Baseten who writes on model performance optimization for LLM, image and video inference
Patrick von Platen
Listed in The Mistral AI Team on the Mistral NeMo model card and as a contributor to the Ministral 3 report (2026), Mistral AI
First listed author of Hugging Face Diffusers; vLLM code owner for Mistral models
Pedro Cuenca
Machine learning engineer, Hugging Face
Machine learning engineer at Hugging Face; Diffusers co-author and builder of on-device Swift tools
Peiyuan Zhang
Works at ByteDance (title not stated), ByteDance
First author of the Sliding Tile Attention and VSA papers cited by FastVideo; Hao AI Lab alumnus
Pete Warden
CEO, Useful Sensors Inc
CEO of Useful Sensors, founding member of the TensorFlow team, and co-author of TinyML and Moonshine
Peter Salanki
Co-founder and Chief Technology Officer (CTO since March 2024), CoreWeave
Co-founder and Chief Technology Officer of CoreWeave, the GPU cloud for AI training and inference
Philipp Schmid
Staff Engineer (Developer Experience and Developer Relations), Google DeepMind
Staff Engineer for developer experience at Google DeepMind; former Technical Lead at Hugging Face
Pierrick Hymbert
Developer (BNP Paribas is the company listed on Hymbert's GitHub profile), BNP Paribas
Contributor to llama.cpp's server, its test and benchmark workflows, and model support
Piotr Wilkin
Systems architect, Syndatis
Maintains llama.cpp's parser code and contributes to Lemonade; systems architect at Syndatis
Priya Nagpurkar
Vice President of AI Platform (as titled by IBM Research in March 2026), IBM Research
Vice president at IBM Research, titled VP of AI platform in March 2026; co-author of LLM-serving research
Radoslav Gerganov
Code owner for the RPC backend (ggml-org/ggml-rpc), llama.cpp project
Code owner for llama.cpp's RPC backend, which offloads computation to remote machines
Rahul Patil
Chief Technology Officer, Anthropic
Chief Technology Officer at Anthropic; previously CTO of Stripe
Rajat Sen
Research Scientist, Google Research
Google Research scientist and one of the creators of TimesFM, the time-series forecasting foundation model
Robert Shaw
Director of Engineering, Red Hat
Red Hat engineering director and llm-d project lead; core committer to vLLM
Robert Wachen
Co-founder and President, Etched
Co-founder and President of Etched, which builds inference hardware for AI models
Rodrigo Liang
Co-founder and CEO, SambaNova
Co-founder and CEO of SambaNova; former processor engineering leader at Sun Microsystems and Oracle
Sid Sheth
Founder and CEO, d-Matrix
Founder and CEO of d-Matrix, which builds memory-centric inference accelerators and racks for AI
Sigbjørn Skjæret
Hugging Face is the company listed on Skjæret's GitHub profile, Hugging Face
llama.cpp code owner for model conversion, gguf-py and core model code; Hugging Face
Simon Mo
Co-founder, Inferact
Lead maintainer of vLLM and co-founder of Inferact, a company started by vLLM's maintainers
Song Han
Associate Professor with tenure, EECS, Massachusetts Institute of Technology
MIT associate professor and NVIDIA research director; co-author of AWQ, SmoothQuant and StreamingLLM
Sudeep Bhoja
Co-founder and CTO, d-Matrix
Co-founder and CTO of d-Matrix, developer of in-memory compute and 3D DRAM inference hardware
TheBloke
Contributor (convert.py, 2023), llama.cpp project
Published quantized GGUF, GPTQ and AWQ versions of open language models on Hugging Face
Tianqi Chen
Associate Professor, Machine Learning Department and Computer Science Department, Carnegie Mellon University
Started MLC LLM, a compiler-based engine for running language models on GPUs, phones, and browsers
Tim Davis
Senior Vice President and General Manager of Modular, Qualcomm
Co-founder of Modular, makers of Mojo and MAX; SVP and GM of Modular at Qualcomm, which acquired it in 2026
Tim Dettmers
Assistant Professor, Carnegie Mellon University
Creator and maintainer of bitsandbytes; Assistant Professor at CMU and Research Scientist at Ai2
Tuhin Srivastava
CEO and Co-founder, Baseten
CEO and co-founder of Baseten, an inference platform for deploying and serving AI models
Vipul Ved Prakash
Founder & CEO, Together AI
Founder and CEO of Together AI, which builds a cloud platform for training and running large models
Waseem AlShikh
CTO and co-founder, WRITER
Co-founder and CTO of WRITER, developer of the Palmyra large language models
Woosuk Kwon
Co-founder and CTO, Inferact
Co-creator and lead maintainer of vLLM; co-founder and CTO of Inferact
Xuan-Son Nguyen
Software engineer, Hugging Face
Software engineer at Hugging Face and core maintainer of llama.cpp
Yagil Burowski
LM Studio team member (shown with the "LM Studio Team" badge on LM Studio Hub), Element Labs
LM Studio team member; made the first commits to LM Studio's lms CLI and MLX engine repositories
Ying Sheng
Officer, LMSYS
SGLang co-author and codeowner; first author of FlexGen, for running large models on a single GPU
Younes Belkada
Machine Learning Engineer, Hugging Face
Listed author of Hugging Face's TRL library and co-author of the StarCoder2, Zephyr, and LLM.int8() papers
Zhuohan Li
AI Research Scientist, Meta
Co-creator and lead maintainer of vLLM; AI Research Scientist at Meta focusing on inference
Support Us
Help keep USASI useful.
Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).
About supporting this project