International Business Machines Corp (IBM  ) is weighing the use of artificial intelligence chips designed in-house to lower the costs of operating a cloud computing service it made available this week.

Mukesh Khare, general manager of IBM Semiconductors, said the company is contemplating using a chip called the Artificial Intelligence Unit as part of its new "Watsonx" cloud service, Reuters cites an interview at a semiconductor conference in San Francisco.

IBM is looking to tap the generative AI technologies boom more than a decade after Watson, its first major AI system, failed to gain market traction.

Khare said using its chips could lower cloud service costs because they are power efficient.

In October, IBM announced the chip's existence without divulging further.

Khare said its partner in semiconductor research, Samsung Electronics Co, Ltd (SSNLF  ), manufactured the chip, and IBM is considering using it in Watsonx.

Khare said the company has several thousand prototype chips already working.

IBM was not trying to design a direct replacement for semiconductors from Nvidia Corp (NVDA  ), Khare added.

Instead, IBM's chip aims to be cost-efficient at what AI industry insiders call inference, which is putting an already trained AI system to use to make real-world decisions.

IBM also looks to replace nearly 8,000 jobs with AI over the next few years, beginning with back-office functions, specifically in the human resources (HR) sector.

Price Action: IBM shares traded higher by 0.30% at $134.85 premarket on the last check Wednesday.