The CEO Behind the Fastest-Growing AI Inference Company | Tuhin Srivastava

The CEO Behind the Fastest-Growing AI Inference Company | Tuhin Srivastava

From Gradient Dissent: Conversations on AI by Lukas Biewald

November 18, 2025 · 59 min · Season 1 · Episode 131

About this episode

Tuhin Srivastava discusses the rise of Baseten and the challenges of AI inference.

In this episode of Gradient Dissent, Lukas Biewald talks with Tuhin Srivastava, CEO and founder of Baseten, one of the fastest-growing companies in the AI inference ecosystem. Tuhin shares the real story behind Baseten’s rise and how the market finally aligned with the infrastructure they’d spent years building. They get into the core challenges of modern inference, including why dedicated deployments matter, how runtime and infrastructure bottlenecks stack up, and what makes serving large models fundamentally different from smaller ones. Tuhin also explains how vLLM, TensorRT-LLM, and SGLang differ in practice, what it takes to tune workloads for new chips like the B200, and why reliability becomes harder as systems scale.  The conversation dives into company-building, from killing product lines to avoiding premature scaling while navigating a market that shifts every few weeks. Connect with us here:  Tuhin Srivastva: https://www.linkedin.com/in/tuhin-srivastava/   Lukas Biewald: https://www.linkedin.com/in/lbiewald/ Weights & Biases: https://www.linkedin.com/company/wandb/

People in this episode

Host: Lukas Biewald

Guest: Tuhin Srivastava

Topics covered

  • AI inference
  • company-building
  • infrastructure challenges
  • model serving
  • market alignment
  • workload tuning

Keywords

  • AI
  • inference
  • Baseten
  • Tuhin Srivastava
  • model serving
  • infrastructure
  • workload tuning
  • scaling

Mentioned in this episode

Organizations: Baseten, Weights & Biases

Products: vLLM, TensorRT-LLM, SGLang, B200

More episodes of Gradient Dissent: Conversations on AI

Explore listener stats, chart rankings, contacts and more on the Gradient Dissent: Conversations on AI podcast page.