Infinity Appoints Former Meta Engineer Aditya Om and CUDA Expert Elliot Arledge to Strengthen AI Chip Software Development

Infinity (Infinity Artificial Intelligence Institute), an automated AI research company building the software layer that makes any AI chip inference-ready, announced two key hires to its engineering team. Aditya Om, a former senior software engineer at Meta Superintelligence Labs (MSL), joins Infinity as Staff Inference Optimisation Engineer, and Elliot Arledge, whose CUDA and LLM coding courses have taught skills to more than two million people, joins as a Member of Technical Staff.

“We’re hiring engineers to solve the greatest engineering challenges of our generation,” said Jeremy Nixon, founder and CEO of Infinity. “Aditya built inference stacks inside Meta Superintelligence Labs’ silicon program. Elliot taught millions of engineers how kernels actually work. Now they’re building automated AI research systems that create stronger AI models and inference frameworks than humans have ever built, so that every chip can run frontier AI."

Om and Arledge join Infinity at a pivotal time, as the company scales Ignition, its autonomous AI agent that compresses years of chip software development into days. Ignition’s coding-agent controller autonomously bootstraps every layer of a chip’s software stack.

Before joining Infinity, Om led development of the software stack for MSL’s in-house training and inference chips, built the collective communications software stack for Lightmatter’s Passage, where he published Envise in Nature, and worked as an IoT systems design engineer at Intel. He holds a Master’s degree in Electrical Engineering and Computer Science from the University of Michigan, Ann Arbour.

“Joining the team was a no-brainer,” said Om. “Inference has taken the world by storm. We have a pivotal shift in front of us, touching all areas of our lives, similar to the internet in the mid-90s. Infinity's mission of automating research in inference optimisation so that the software layer is shaped to the custom hardware is the groundbreaking work I am passionate about.”

Arledge is a self-taught kernel engineer and CUDA expert who, at 22, has built coding courses that have taught millions of people to train LLMs from scratch & optimise CUDA kernels. “Chips are the core bottleneck of our time, and that’s exactly why I wanted to join Jeremy and Infinity,” said Arledge. “It takes a stubborn team of highly skilled, highly coordinated, ambitious people to pull this off.”