Nvidia's Huang pitches AI tokens on top of salary as agents reshape how humans work

The perks of working in Silicon Valley have long included high salaries. Now, some engineers may be offered a new incentive: artificial intelligence tokens.
Nvidia CEO Jensen Huang on Monday floated a novel compensation model that would give engineers a token budget on top of their base salary, effectively paying them to deploy AI agents as productivity multipliers.
Tokens, or units of data used by AI systems, can be spent to run tools and automate tasks and are becoming "one of the recruiting tools in Silicon Valley," Huang said.
"[Engineers] are going to make a few hundred thousand dollars a year, their base pay," Huang said at the chipmaker’s annual GPU Technology Conference.
"I'm going to give them probably half of that on top of [their base pay] as tokens ... because every engineer that has access to tokens will be more productive."
The pitch signaled Huang's broader vision of the workplace, in which engineers oversee a fleet of AI agents capable of completing complex, multi-step tasks autonomously with minimal user input.
It is a vision that Huang has been building toward publicly. Last month, he told CNBC that Nvidia's employees would one day work alongside hundreds of thousands of AI agents.
"I have 42,000 biological employees, and I'm going to have hundreds of thousands of digital employees," he said.
The comments come as concerns grow that AI agents — software systems capable of independently executing complex, multi-step tasks — will hollow out white-collar work.
In a memo to investors, Howard Marks, founder of Oaktree Capital Management, warned of "an incredible leap ahead in AI's capabilities" that now allows it to "act autonomously" — a distinguishing point that determines its ability to substitute human labor.
"That difference is what separates a $50 billion market from a multi trillion dollar one," the veteran investor said.
Goldman Sachs estimates AI could potentially automate tasks accounting for 25% of all work hours in the U.S., enough to fuel fears of what some have grimly dubbed a "job apocalypse."
The bank sees a 15% productivity boost from AI, which could lead to 6% to 7% of jobs displaced over the adoption period.
"Risks are skewed toward greater displacement if AI proves more labor-displacing than prior technologies," said Joseph Briggs, Goldman's senior global economist.
Some 60% of today's workers are employed in occupations that didn't exist in 1940, Briggs said, citing a study by economist David Autor, suggesting that AI will render some roles obsolete while creating others that don't yet exist.
AI agents drive software demand
Huang has taken an optimistic view of the impact of AI agents on the software industry, describing it as "counterintuitive." Rather than reducing demand for software, AI agents will become its most voracious customers.
His logic goes: more AI agents mean more demand for the underlying software infrastructure they run on — the programs, tools, and computing resources that power them.
"The number of C-compilers that we use, the number of Python programs that we have, the number of instances, are growing very, very fast — because the number of agents we have that use these tools are going up," he said.
Bruno Guicardi, president and founder of the information technology company CI&T, described the change as nothing short of a paradigm shift. "A new layer of abstraction is being created through agents," he said.
"Now software engineers can 'tell' what computers should do, not in a programming language but in plain English. Work that used to take months to be done now takes a couple of days. And we see it only accelerating from here."
'Talent paradox'
The AI-fueled anxiety over labor displacement has been hard to contain, even as companies struggle to find skilled workers.
The job market is currently experiencing a "talent paradox" where 98% of C-suite executives expect AI to lead to headcount reductions over the next two years, while 54% cite talent scarcity as their top macro challenge, said Lewis Garrad, career practice leader at consultancy Mercer Asia.
Around 65% of executives expect 11% to 30% of their workforce to be redeployed or reskilled due to AI by 2026, Garrad estimated.
Entry-level jobs face the greatest risk as AI eliminates the "stepping-stone" tasks historically used to train new workers, further widening the skills gap at a time when demand for AI-literate workers is accelerating, Garrad added.
Roles involving data analysis, document processing, information comparison, and drafting initial reports are at risk of being "first in line" for displacement, said Andreas Welsch, founder of consultancy Intelligence Briefing and author of The Human Agentic AI Edge.
Goldman's Briggs also acknowledged the transition won't be frictionless, even under the most optimistic scenario, anticipating a peak gross jobless rate that will increase by around half a percentage point as the job market transitions into a new era.
But new jobs will emerge, Briggs said, stressing that technological change has always been a main driver of job growth in the long-run through the creation of new occupations.
Tens of millions of people are now employed in sectors such as computing, the gig economy, e-commerce, content creation and video games — industries that were science fiction a generation ago.
That said, integrating AI capabilities into existing corporate workflows may ultimately prove harder than the technology itself. Roughly 80% to 85% of AI projects have failed since 2018 — a sobering statistic for an industry awash in enthusiasm, noted Intelligence Briefing's Welsch.
"It would be undesired to have hundreds of thousands of agents that create more problems than they solve," he said.