Harshit Rathod
Senior engineer at Salesforce. Writing about AI, backend engineering, and modern web dev.
Latest Post
All posts →
AI
Two Workloads in a Trench Coat: Why Prefill and Decode Change Everything
LLM inference is two opposite workloads — compute-bound prefill and memory-bandwidth-bound decode. Here's how continuous batching, PagedAttention, and disaggregation evolved to deal with it.
Read the post →
About
10+ years building distributed systems at scale. Currently a Senior Member of Technical Staff at Salesforce, previously Walmart Global Tech. I write about AI, backend engineering, and modern web dev — usually with a focus on the tradeoffs production teams actually face.