RL & data meetup: SkyRL x Mercor x Harbor

Pretraining gives models basic knowledge.

Post-training turns that knowledge into unique differentiation. Teams are combining proprietary datasets and user activity with models to scale RL runs. That means orchestrating evals, rollouts, sandboxes, and both training and inference workloads all at once.

Join us for an evening of technical talks and networking with ML engineers, researchers, and builders from Harbor, Mercor, and SkyRL to see how they’re pushing the frontier of post-training.

Agenda:

5:30 PM – Doors open, food, and networking

6:00 PM – Mercor

6:20 PM – Anyscale/SkyRL

6:40 PM – Harbor

7:00 PM – Open networking

... more details on speakers and topics coming soon!

Hosted by:

Anyscale, the company behind the Ray open source project, is a fully managed AI platform for foundation model-scale workloads. AI teams use it to run data, training, inference, and RL workloads at scale on any cloud.

Harbor builds open-source infrastructure for specifying sandboxed agent tasks for evaluation and optimization, from the makers of Terminal-Bench.

Mercor