Frontier Evals and RL with Researchers and Engineers from Google DeepMind, Cohere, and LinkedIn
As models approach capability plateaus, the frontier is shifting to post-training: reinforcement learning, evaluation frameworks, and feedback systems that determine how models behave in the real world.
The next breakthroughs will not come from scale alone, but from how we measure, reward, and shape intelligence.
Join us for a closed-door conversation with leaders working at the frontier of evaluation, alignment, and reinforcement learning across industry and research.
Speakers:
David Reitter - Senior Staff Research Scientist at Google DeepMind. Connect with David.
Wei-yin Ko - Member of Technical Staff at Cohere. Connect with Wei-yin.
Misam Abbas - Staff AI Engineer at LinkedIn. Connect with Misam.
Moderator:
Viviana Marquez - DevRel Engineer at Prolific. Connect with Viviana.
Together, we’ll explore what the next generation of evaluation and RL systems means for the future of AI: where models improve, where they fail, and how human feedback, reward modeling, and scalable evaluation pipelines will shape the next era of intelligent systems.
Agenda:
6:00 – 6:45: Arrival, Networking and Refreshments
6:45 – 7:00: Welcome and Introductions
7:00 – 7:45: Panel
7:45 – 8:00: Q&A
8:00 – 9:00: Networking and Refreshments
Attendance is limited and curated.
Requests will be reviewed.
About our hosts:
Prolific powers high-quality human data for model evaluation and training. AI Circle curates high-agency operators across research, startups, and enterprise. Together, we’re convening a room designed for signal.
Our event will be hosted at the SignalFire office in Nomad. They raised a $1B fund last year focused on AI and data.
Limited capacity.
Apply to attend.
Marketing Disclaimer
By submitting this form, you agree to receive marketing communications from SignalFire. You can unsubscribe at any time by clicking on the unsubscribe link at the bottom of our emails. See our privacy policy available on our website.