CoreWeave Launches First Publicly Available Serverless Reinforcement Learning Capability to Build Reliable AI Agents

First Joint Offering from Weights & Biases and OpenPipe, Provides Fast, Easy Way to Train with RL at Scale

LIVINGSTON, N.J.--(BUSINESS WIRE)--CoreWeave, Inc. (Nasdaq: CRWV), the AI Hyperscaler™, today announced the launch of Serverless RL, a fast and easy way to train AI agents using reinforcement learning (RL).

The first publicly available fully managed RL capability, Serverless RL scales seamlessly to dozens of GPUs, requires only a Weights & Biases account and API key to get started, and delivers faster feedback loops with lower barriers to entry for developers. This new capability launches just weeks after CoreWeave’s acquisition of OpenPipe, combining its leading RL tools with the Weights & Biases AI developer platform, powered by CoreWeave’s AI cloud.

Reinforcement learning is critical to making AI agents more reliable, but it has historically been out of reach for most organizations. Running RL ordinarily requires access to costly infrastructure, deep expertise, and time-consuming workflows that slow down iteration. Serverless RL helps to remove those constraints so more enterprises can continuously improve AI agents and deliver a better customer experience.

“Being fast to market is critical, and equally important is the elegance and ease of use we are now giving AI pioneers across labs, enterprises, and startups to fine-tune large language models and build AI agents with confidence,” said Peter Salanki, Co-founder and Chief Technology Officer of CoreWeave. “We are integrating infrastructure, RL frameworks, and developer tools for the AI era to help enterprises of any size unlock the value of AI agents. This sets CoreWeave apart.”

Benchmarks show nearly 1.4x faster training times and 40 percent lower costs compared to local H100 GPU environments, with no impact on model quality. This was achieved by solving the long-standing “straggler problem” in RL training. By multiplexing many training runs across CoreWeave’s production-grade cluster environment, the system maintains high utilization in aggregate and only charges for incremental tokens generated. This delivers both improved throughput and significantly reduced cost in practice.

Customers ranging from AI-native companies to Fortune 500 enterprises are already showing strong interest in Serverless RL. For example, SquadStack.ai, an AI-powered contact center platform that delivers hyper-personalized experiences for leading consumer brands, will use Serverless RL to enhance customer engagement. As will QA Wolf, a hybrid platform that helps technology teams ship better software faster.

“We’re excited about Serverless RL on CoreWeave to improve the quality of our agents, and eager for instant GPU access without the burden of managing infrastructure ourselves,” said Jon Perl, CEO of QA Wolf.

CoreWeave is committed to serving as the essential AI cloud used by builders to develop and deploy AI across every industry. The company continues to add capabilities to its platform, including through acquisitions such as OpenPipe for reinforcement learning, Weights & Biases for agent and model iteration, evaluation, monitoring, and inference, and this week, adding Monolith, a pioneer in AI and machine learning for complex physics and engineering challenges.

To learn more about Serverless RL, visit www.wandb.ai/site/serverless-rl.

About CoreWeave

CoreWeave, the AI Hyperscaler™, delivers a cloud platform of cutting-edge software powering the next wave of AI. The company's technology provides enterprises and leading AI labs with cloud solutions for accelerated computing. Since 2017, CoreWeave has operated a growing footprint of data centers across the US and Europe. CoreWeave was ranked as one of the TIME100 most influential companies and featured on Forbes Cloud 100 ranking in 2024. Learn more at www.coreweave.com.