Thinking in Tokens

Building the Enterprise GenAI Stack for 2026

Enterprises are racing to adopt GenAI, but most are still stuck in pilot purgatory. In this episode, we sit down with Sujeet — ML Architect at Dell and former Data Scientist at HP — to unpack what it actually takes to build a scalable GenAI stack for 2026. We dig into the realities behind RAG architectures, NL-to-SQL systems, workflow orchestration, embeddings, time-series foundations, and serving LLMs as production-grade APIs. Sujeet breaks down the difference between flashy demos and platforms that ship, drawing on nearly a decade of building ML systems that impact global operations. If you're building AI inside a large org, leading an ML team, or trying to take a GenAI initiative from POC to platform, this episode is your blueprint. No hype — just the architecture, tradeoffs, and lessons from the trenches. Follow- Bupender: linkedin.com/in/bhupender-sharma-02497723 [https://www.linkedin.com/in/bhupender-sharma-02497723] Sujeet: linkedin.com/in/sujeet-jog-83276a5a [https://www.linkedin.com/in/sujeet-jog-83276a5a] Codebase: https://www.codebase.com/ [https://www.codebase.com/]

Welcome to Thinking in Tokens: Where AI Gets Real

Welcome to Thinking in Tokens, hosted by Bhupender Sharma — a podcast for the builders, thinkers, and leaders shaping the future of AI. In this short introductory episode, Bhupender shares what Thinking in Tokens is all about: deep, technical, and honest conversations about how AI, Generative AI, and Machine Learning are being built, implemented, and applied across industries. Expect no hype — just insights from CTOs, founders, and experts who are defining what’s next in technology. Subscribe now to join a growing community of engineers, founders, and innovators who are ready to go beyond the noise — and start thinking in tokens.