Forward Deployed Engineer

Anurag Singh Chauhan

I build production AI systems — the agents that talk to customers, the integrations that put AI inside the tools teams already use, and the backends that keep it all running when traffic spikes at 2am.

  • 100+ calls/day handled by a production voice agent
  • 2.5 yrs founding → lead → forward-deployed
  • 0 data loss on a live DB migration
  • 35%+ infra cost cut across rewrites

About

I'm Anurag — a Forward Deployed Engineer and the founding engineer at Debales AI. For the last two and a half years I've built AI products end to end: the agents that talk to customers, the integrations that put AI inside the tools merchants already work in, and the systems that keep all of it running under real load.

That's meant wearing whatever hat the work needs. Some weeks I'm deep in backend architecture, designing systems that process high volumes of events without falling over. Other weeks I'm operating cloud infrastructure, fixing what observability surfaces, and making sure the platform holds up. Lately, more of my time has shifted to working directly with customers — sitting in their calls, understanding what's actually broken in their day, and turning that into product.

I came up leading a small engineering team along the way, which taught me the thing I keep coming back to: the best technical work isn't the cleverest code, it's the work that unblocks other people and survives contact with reality. The wins I'm proudest of look unglamorous on paper — a backend rewrite that cut infrastructure costs, a monorepo migration that dropped deployment issues, an integration that lifted onboarding. None are interesting to talk about at a party. All of them moved the business.

What excites me now is how much of AI's real value lives in the integration layer — the edge cases, the customer-specific quirks, the loop between what someone says they need and what they actually need. That's the work I want to keep doing.

Experience

May 2025 — Present

Debales AI

Forward Deployed Engineer

  • Own end-to-end customer deployments: integration, customization, production debugging, and post-launch iteration on real usage signal.
  • Drove architecture for enterprise integrations (Outlook, SharePoint, Power BI) so AI agents pull live data from tools merchants already use.
  • Built an AI email follow-up system that handles ~80% of initial replies autonomously and forwards only qualified leads to reps.
  • Driving an Azure cost-optimization initiative cutting monthly spend ~37% ($4K → $2.5K) with no loss of feature coverage.

May 2024 — May 2025

Debales AI

Founding Lead Engineer

  • Led a team of 4 engineers within a 7-person cross-functional unit — set technical direction, ran code review, and mentored on hard problems.
  • Architected the centralized high-throughput backend (NestJS, BullMQ, Redis) the platform still runs on.
  • Led a zero-downtime DynamoDB → MongoDB migration with no data loss on a live product.
  • Migrated the codebase to a monorepo — 40% fewer deployment issues — and set org-wide standards that cut debugging time ~30%.

Nov 2023 — May 2024

Debales AI

Founding Engineer

  • First engineer alongside the founders; made the foundational architecture decisions the company still runs on.
  • Designed and shipped the early serverless backend (AWS Lambda, Node.js), cutting infrastructure costs 35% at a critical early stage.
  • Maintained and extended the core application end to end as the product evolved.

2021 — 2025 · CGPA 8+/10

Education

B.Tech, Computer Science & Engineering

Accurate Institute of Management and Technology, Greater Noida

Joined Debales AI as founding engineer during the degree; promoted to lead engineer in the final year.

Stack

Languages

  • TypeScript
  • JavaScript
  • SQL
  • C / C++

AI & Voice

  • Azure OpenAI
  • LiveKit
  • Twilio
  • Deepgram (STT)
  • ElevenLabs (TTS)
  • LLM integration

Backend

  • Node.js
  • NestJS
  • BullMQ
  • Redis
  • GraphQL
  • REST
  • WebSockets
  • Serverless

Frontend & Mobile

  • React
  • Next.js
  • React Native
  • Expo

Cloud & Infra

  • Azure
  • AWS
  • Terraform
  • Docker
  • OpenTelemetry

Databases

  • MongoDB
  • PostgreSQL
  • Redis
  • DynamoDB

Contact

Building AI products that survive contact with reality. Let's talk.