Brij Kishore Pandey's Recent LinkedIn Posts

For years, most conversations stopped at: CPU vs GPU. But modern AI infrastructure is much bigger than that now. Today, different processors solve very different parts of the AI workload. CPU handles orchestration, preprocessing, operating system tasks, and general-purpose logic. GPU handles massive parallelism,…

Claude Code isn't a coding assistant. It's a full agent development platform — and most people are only using 10% of it. Here's the architecture that changed how I think about it: 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 + 𝗦𝗸𝗶𝗹𝗹𝘀 + 𝗛𝗼𝗼𝗸𝘀 + 𝗦𝘂𝗯𝗮𝗴𝗲𝗻𝘁𝘀 + 𝗣𝗹𝘂𝗴𝗶𝗻𝘀 = The Agent Development Kit Let me break down each l…

Two years ago, backend engineering looked very different. Most of the work was around: APIs Databases Queues Caching Auth Cloud Security Observability That foundation is still extremely important. But now, a new layer is being added on top of it. LLM APIs. Embeddings. Vector databases. RAG. Context engineering. To…

Two years ago, backend engineering looked very different. Most of the work was around: APIs Databases Queues Caching Auth Cloud Security Observability That foundation is still extremely important. But now, a new layer is being added on top of it. LLM APIs. Embeddings. Vector databases. RAG. Context engineering. To…

Forward Deployed Engineer may become one of the most important AI roles of the next few years. Not because companies need more AI demos. Because companies need people who can take AI into messy real-world environments and make it actually work. A Forward Deployed Engineer sits at the intersection of: Software engi…

For years, most conversations stopped at: CPU vs GPU. But modern AI infrastructure is much bigger than that now. Today, different processors solve very different parts of the AI workload. CPU handles orchestration, preprocessing, operating system tasks, and general-purpose logic. GPU handles massive parallelism,…