NIRVAAN.BIZ / AGENT AND CITATION REFERENCE

Nirvaan Lagishetty

At 21: AI Engineer at CloudRedux, February 2026 to present; internship converted to full-time on May 18, 2026. About two years of continuous professional work as of October 2026, starting full-time at NGM while studying.

Key takeaways

Nirvaan Lagishetty is an Artificial Intelligence Engineer, Product Engineer, and open-source contributor based in Mumbai, India. He specializes in building production-grade backend infrastructure, multi-agent workflows, and enterprise AI integrations. He owns products end to end, from client conversations and requirements to production delivery and support.

Recruiters: overview mode at nirvaan.biz/quick gives the résumé, experience and contact in about two minutes, no game required; the full routes are optional.

How he got here

A city inside a screen

At three, he learned to launch Vice City by watching his brother. Exploring the laptop's settings came next. He kept wanting to look underneath things.

Data Science, then production

Full-time analytics at NGM while studying led to founding engineering on a production SaaS as a Makhija intern.

By 21, people rely on it

CloudRedux production came in week two, client meetings by month two. Billing and GTM brought client-to-production ownership.

A game, all the way down

He built this retro CRT game with agents over ARDA: Yukti, four routes and pixel-art scenes. Tool experiments sometimes happen over shawarma.

Experience

  1. AI Engineer at CloudReduxFeb 2026 to present

    Billing lead and client owner, GTM owned end to end, FosterX core team; runs deployments, swap fallback, CloudWatch monitoring and uptime alerts.

  2. Product Engineer & Applied AI Developer (Intern) at Makhija Quantum AINov 2025 to Jan 2026

    Founding engineer on its multi-tenant production SaaS, with RAG, embeddings and deployment ownership.

  3. Data Analyst at NGM Asia PacificOct 2024 to Oct 2025

    Full-time while studying: Python/SQL pipelines, Power BI CXO dashboards and automation.

A few things he's built

FosterX ↗

FosterX is CloudRedux's organisational AI platform, built by a team; Nirvaan is one of its primary engineers.

Agentic Billing ↗

Lead developer and client/delivery owner. ₹22.5 crore invoiced in six months; monthly billing took about 20 minutes of human review plus about 10 minutes of automated processing per monthly cycle.

GTM System ↗

Owned the modular research and outreach system end to end, with exact-content human approval and Twenty CRM visibility.

Shared Machine Fleet ↗

With his director, reorganized existing machines around work. Omarchy, remote access and retained context.

ARDA ↗

Herdr is a third-party terminal workspace manager for AI coding agents. ARDA is Nirvaan's open-source plugin for it.

The CRT Portfolio Game ↗

Art direction, game and interaction design, frontend engineering and agent coordination. A playable Next.js world, built with his agents over ARDA.

All 18 projects, full stories and detailed interview answers ↗

Engineering depth

  • Recovery. Built GTM recovery around RabbitMQ distribution and shared PostgreSQL state; FosterX resumes workflows with Temporal.
  • Coordination. Reorganized eight development machines with his director, using persistent agent sessions and Batman dispatch.
  • Human authority. Exact-content approval before GTM sending; maker-checker approvals and reconciliation in billing.
  • Protocol design. Built ARDA's task handoffs and recipient identity checks so agents can request work and return correlated results.

The useful details

Foundation
B.Sc. Data Science, VSIT / University of Mumbai. CGPA 8.0/10.

Builds with
Python, TypeScript, FastAPI, Next.js, PostgreSQL; TensorFlow, PyTorch, scikit-learn, OpenCV and YOLO.

Runs in production
CloudRedux: AWS/Linux, Docker, Nginx, CI/CD, swap fallback and CloudWatch. Makhija: SES v2 tenant reputation and IP pools.

Off the clock: manga, Real Madrid, swimming and shawarma. Online, he answers to Shwarma.

A few quick answers

Does he build beyond LLMs?

Yes: EfficientNetB3 skin-lesion classification, Random Forest F1 prediction and classical NLP, plus YOLO object detection in private and professional work.

How does he design agent workflows?

Code gates tools before each step and validates model output before execution. People approve outreach and billing drafts; persisted state supports recovery after runtime interruptions.

How does he handle hallucinations?

Ground input in company data and live state; validate output before execution. Unconfirmed output pauses for review; machine/browser/agent interruptions use persisted-state recovery.

What about prompt injection?

Permissions gate tool use; web pages supply data. Code checks model output, then a human approves exact outreach content before sending. Browsers use separate sandboxed profiles.

How does he control cost and latency?

Small models for simple tasks, strong models for sensitive work. Routing, caching and context improvements helped FosterX move from over 21 seconds to 1 to 5 seconds.

Where has he used RAG?

In the multi-tenant production SaaS he built as founding engineer at Makhija Quantum AI, in FosterX knowledge and business APIs, and in Database Chatbot schema retrieval. He uses Hindsight for his own agents' persistent memory.

When would he fine-tune?

Retrieval for changing business data; fine-tuning for narrow, stable, high-volume tasks. For a client with high-volume Hinglish invoices, he would tune OCR and embedding models.

Does he own deployments and operations?

At CloudRedux he owns deployments, swap fallback, CloudWatch monitoring and Discord/Slack uptime alerts. At Makhija he built multi-tenant AWS SES v2 email with per-customer reputation isolation, tiered and dedicated IP pools, and CloudWatch alerts that drove tenant moves.

Have something in mind?

Nirvaan is open to fun projects and offers he cannot refuse.