Aman Tyagi

Senior Software Engineer · AI & Backend · India

amantyagi2k@gmail.comgithub.com/amantyagi22linkedin.com/in/aman-tyagi-700a06190amantyagi.me

Senior software engineer with 3+ years building production RAG, LLM agents and multi-tenant backends on Node.js, Python, MongoDB and AWS. Takes features from prototype to production and leads cross-team releases.

Experience

Delightree — Senior Software Engineer

06.2025 — present

  • Launch-risk agent. An AI agent that predicts which franchise openings will run late, ranks what is blocking them and drafts the follow-ups. Took it from my own prototype to beta. (late openings get flagged before they are late)
  • Multi-tenant RAG engine. Ask a question in plain English, get an answer pulled from the company's own manuals. (no franchise can ever see another's documents)
  • Integration platform. One shared way to connect outside tools — HubSpot, QuickBooks, Zapier, Zenoti and Read AI. (a new provider is four files)
  • Async analytics pipeline. Moved the heavy number-crunching to the background, on a schedule. (reports never slow down the app)
  • Support ticketing domain. Designed and built the whole support-ticket system, start to finish. (a whole support product, built from nothing)
  • Data-model migration. Flattened nested records into one collection, so the app reads them in one go. (two round trips became one $lookup)
  • Partner ingestion API. A documented way for outside companies to send us their data safely. (partners integrate without us writing code)
  • Security hardening. Found and closed three security gaps, including passwords leaking into our logs. (closed them before anyone else found them)
  • Agent tooling. A prototype that lets AI agents use the product's own features as tools, plus a test set for grading LLM answers. (agents got access without backend changes)
  • Release integration. Reviewed and merged the team's work across four repositories, and wrote the design docs. (50+ teammate PRs reviewed and shipped)

Playo — Software Engineer

09.2024 — 06.2025

  • Dense-ranking leaderboard. Precomputed the rankings and kept them in fast memory, instead of rebuilding them every visit. (the slowest screen became the fastest)
  • Geospatial search. Made 'find places near me' actually fast. (search stopped feeling broken)
  • Chat migration. Moved every user's chat history to a new provider without taking the app down. (600k users moved, nobody noticed)

Teal India — Software Engineer

02.2023 — 08.2024

  • Real-time analytics. Live dashboards that kept updating correctly even as we added more servers. (dashboards stayed live as servers scaled out)
  • Legal document-extraction framework. Software that reads legal documents and writes the reports itself. (350+ reports a day, no one touching them)

Earlier: Founding Engineer, Duckcart (2022) · DevOps Engineer Intern, Recruit CRM (2022–23).

Skills

core
JavaScript / TypeScript, Python / FastAPI, Node.js / Express, GraphQL (Apollo), Distributed Patterns
data
MongoDB, Aggregation / Indexing, BigQuery, Weaviate
async
Redis, BullMQ, Cron, Webhooks
platform
AWS, Docker
ai
RAG, Vector Search, AWS Bedrock, AI Agents, MCP, LLM Evals / Langfuse

Focus Areas

AI Agents · RAG & LLM Evals · Performance Engineering · Platform & APIs

Writing (in progress)

Redis caching strategies · MongoDB aggregation optimization · Scaling Socket.io systems · Event-driven architectures in Node.js