Sidhant Singh Rathore
SDE-1 / Applied AI Engineer who builds from scratch idea → architecture → production → iteration. Full-stack across AI, backend, and frontend, currently on AI agents, LLM infrastructure, and real-time systems that hold up at scale.
React
Next.js
TypeScript
Node.js
Python
LangChain
Hugging Face
TailwindExperience
Geekashram
FreelanceJul 2026 – Sep 2026Built their app a live learning platform running 1:1 mentorship and group classes, with post-session analysis that scores class quality and checks mentor feedback against what actually happened plus two landing pages.
Outscale.ai
Applied AI EngineerJul 2025 – Jul 2026Built a real-time AI sales copilot that reads a discovery call as it happens and feeds the rep context, prompts, and next moves while the call is still live. Backend in TypeScript and Python, copilot dashboard in React.
Projects
A macOS desktop app that transcribes live calls, detects customer objections, suggests follow-up questions, generates meeting summaries, and coaches the rep while the call is still running.
A RAG system that lets users upload PDFs and get accurate, context-grounded answers through semantic search and LLM question answering.
A single API interface across multiple LLM providers, with request routing, model selection, API key management, and usage tracking.
Writing
Making a Site Legible to AI Crawlers: What I Found Rebuilding My Own
Aug 30, 2026Crawlable and legible are different problems. A build report on entity graphs, llms.txt, and the positioning bug that had answer engines describing me as a vendor instead of an engineer.
How We Cut Voice-Agent Latency to Sub-500ms: A Production Architecture
Jun 7, 2026A case study in building real-time voice agents: batching, model tiering, flush timers, and keeping the hot path off disk.
Neural Networks: 1 to 100
May 15, 2026A complete ground-up guide to neural networks — from what a single neuron is, to how a full network learns through activation functions, backpropagation, and gradient descent.
2 more posts