Jul 2025 – Present · 11 mos · India · Remote

• ▹Led the launch of Roadmap AI, a fully personalised learning assistant powered by RAG (Retrieval-Augmented Generation), OpenAI’s text-embedding-ada-002, Chroma Vector DB, and Modal for real-time, scalable inference.
• ▹Architected a self-learning dynamic RAG pipeline: [JSON → Embedding → Chroma DB → Query Context Retrieval → Prompt Masking → Model → Nested JSON Output]
• ▹Dynamically decides whether to retrieve existing context or generate a roadmap from scratch, enabling zero-friction personalization for every user query.
• ▹Injects prompt templates based on match confidence and automatically re-embeds new data into the vector store — making the system truly adaptive and self-updating.
• ▹Integrated MCP (Modular Content Pipeline) to process and vectorize 100+ roadmaps, enabling semantic search and structured AI roadmap generation.
• ▹Engineered a Model Context Protocol (MCP) to standardize context injection for the model — combining retrieved chunks, user metadata, prompt masks, and query scaffolding — ensuring consistent and accurate outputs at sub-second latency.
• ▹Developed token-based access with one-time/monthly/yearly tiers, including real-time token usage tracking, speed controls, and upsell modals for premium upgrades.
• ▹Achieved <1s latency for AI responses at scale, improving retention and enabling smooth, conversational AskAI interactions.
• ▹Built an AI-powered DSA Code Editor supporting Run/Submit/Save, tightly integrated with Roadmap AI and backed by gpt-3.5-turbo, o3-mini, and o1 models for contextual code assistance.
• ▹Enhanced AskAI with contextual node + discussion integration, improving answer relevance and surfacing smarter suggestions.
• ▹Resulted in 3x higher roadmap completions, reduced user drop-offs, and transformed the platform into a self-evolving AI-first learning ecosystem.

Jul 2024 – Jul 2025 · 1 yr · India · Remote

• Built flagship "Roadmaps" feature, delivering 100+ curated learning paths across DSA, Development, and System Design used by 100K+ users, while reducing API response time from 2.1s to < 300ms, resulting in a 7x faster experience and 40% higher user engagement.
• Developed and integrated the "AskAI + Discussion Forum", an intelligent peer-programming assistant where users can interact with AI to solve DSA/Dev doubts and collaborate with others.
• Worked on complex APIs to reduce processing time and improved tab switching experience for smoother navigation
• Build a Session Recording Bot using Python, Selenium, and headless Azure VMs with deep link automation, automating session joining and recording, cutting down 100% of manual effort and improving reliability.
• Optimised 150+ APIs by implementing advanced caching layers, async processing, and API pipelines, reducing backend latency by up to 70% and improving system throughput.
• Reduced core web vitals TBT, LCP, and FCP from 4.4s to 990ms through advanced frontend optimisations (SSR, dynamic imports, lazy-loading APIs), significantly boosting UX for 15K+ monthly active users.
• Led the end-to-end performance overhaul of the platform, focusing on smoother tab-switching experiences, minimal downtime, and blazing-fast navigation across the app.
• Migrated MongoDB from Atlas to self-hosted replica sets, wrote automated backup & recovery scripts, set up VMs, and integrated cron-based backups to Azure Blob, ensuring data durability and cost-efficiency.
• Set up real-time monitoring and alerting with Prometheus and Grafana, ensuring system health, proactive issue resolution, and enhanced Error result.
• Deployed scalable CI/CD pipelines using Azure, GitLab, and Vercel, ensuring zero-downtime deployments and faster iteration cycles across teams.
• Handled end-to-end production deployment and scaling for a system serving 15K+ users, maintaining high availability, fault tolerance, and robust performance at scale.

Feb 2024 – Jun 2025 · 1 yr 4 mos · India · Remote

• I mentor students for DSA interview preparation and offer mentoring for development, resume reviews, career and placement guidance, as well as remote job search strategies.