Staging environment
Free Lesson

Optimizing Open Models for Production

Hosted by Aish & Arvind and Sujee Maniyam

Mon, Oct 5, 2026

4:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Mastering Agentic AI: Certification by The Gen Academy
Aishwarya Srinivasan and Arvind Narayanamurthy
View syllabus

What you'll learn

Understand Modern Inference Optimization

Learn the techniques that improve latency, throughput, memory efficiency, and cost when serving large open models.

Optimize Frontier Open Models at Scale

Explore caching, quantization, optimized kernels, disaggregated serving, & speculative decoding for production workloads

Learn from the Kimi K3 Production Stack

See how recent inference optimizations helped bring the 2.8T-parameter Kimi K3 model into production efficiently.

Why this topic matters

Open models are getting dramatically larger and more capable, which makes serving them efficiently a systems problem of its own. This session explores modern inference techniques used to make state-of-the-art open models practical in production, covering caching, kernels, quantization, speculative decoding, and disaggregated inference, with lessons from the recent Kimi K3 launch and its production-scale vLLM integration.

You'll learn from

Aish & Arvind

AI Engineers | Building & Teaching @ The Gen Academy

Aishwarya Srinivasan is the Co-founder of The Gen Academy and a globally recognized AI educator with a community of 1.2M+ professionals. Previously, she led AI Developer Relations at Fireworks AI and built AI products and ecosystems at Google, Microsoft, and IBM. She holds a Master’s in Data Science from Columbia University.

Arvind Narayanamurthy is the Co-founder of The Gen Academy, former AI Solutions Architect at Ema, and Founder of Eikos Health. He has built and deployed enterprise AI systems across Microsoft, IBM, and Adobe, combining deep technical expertise with a practical approach to production AI. He holds a Master’s from Carnegie Mellon University.

Sujee Maniyam

Developer Relations @ Nebius

Sujee Maniyam is an AI Developer Advocate at Nebius with deep experience across AI, distributed systems, data engineering, and cloud infrastructure. A developer educator, author, and open-source contributor, he regularly speaks and teaches on open models, AI infrastructure, inference optimization, and building production-ready AI systems.

See all products from Aishwarya Srinivasan & Arvind Narayan

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.