Skip to content
Shivam Gupta

AI & Automation Engineer

Building production automation, retrieval-grounded agents, and the internal platforms they feed.

SG
Shivam Gupta
AI & Automation Engineer
Open to AI & Automation roles

Vision

I build automation that runs unattended against real operational data — student lifecycles, fee collection, telephony reporting — and the internal platforms that make its output usable by the people doing the work.

Workflow designLLM agentsSystems integration
10
Automations in production
13
Branches automated
1,200+
Domains managed
6
Platforms shipped
Detailed context

The thinking behind my automation work

I started as a React JS Developer at SNVA Ventures in September 2024, building client-facing applications and internal dashboards. I joined SkillCircle in February 2025 as an IT Executive, running hosting for 1,200+ domains across cPanel, DNS, SSL and Linux. I began automating the repetitive parts of that job; the automations became core operations, and in January 2026 the company created the AI & Automation Engineer role for it.

Automation against live systems

Ten of 49 workflows running on daily, scheduled and real-time triggers across Edmingle, Google Workspace, MCube telephony and WHMCS — no sandbox, no manual kick-off.

Agents that refuse to guess

Retrieval-grounded answers with structured output and an explicit escalation flag, so refunds, complaints and account issues route to a human instead of receiving an invented reply.

Platforms the output lands in

Next.js and NestJS applications on Supabase — job portal, admission dashboard, sales portal — owned from data model and migrations through interface and deployment.

Signals I optimise for

Correctness over clevernessUnattended operationException-only alertingVerified inputsReversible changesDocumented behaviourZero manual kick-off

How a build actually runs

  1. 1Sit with whoever does the task today and trace it end to end, including the steps nobody wrote down.
  2. 2Build a read-only version first: probes confirm the data is shaped the way I think it is.
  3. 3Enable writes against a small slice, verify the output by hand, then widen.
  4. 4Ship on a schedule or webhook, report what it did, and escalate only the exceptions.
Engagement snapshot

How I create leverage

Primary focus
Production automation and retrieval-grounded agents against live business systems.
Work style
Documentation-led. PRD, data model and engineering rules written alongside the build.
Collaboration
Close to the people doing the manual work, because that is where the requirements actually are.
Best fit
Teams with real operational load and no one owning the automation layer yet.
Open to AI & Automation roles

Happy to walk through any workflow or platform on this site, live.

Academic foundation

Education

Degree
B.Tech, Electrical Engineering
Institution
Rajkiya Engineering College, Sonbhadra
Timeline
2020 – 2024
Before that
Intermediate, Science · 2018 – 2020
Communication

Languages

  • HindiNative
  • EnglishProfessional

Technical Stack

Technologies and tools I use to build production systems.

n8n49 projects
Proficiency92%

49 workflows built, eight live on scheduled, webhook and real-time triggers.

RAG pipelines1 project
Proficiency78%

Qdrant vector store, Gemini embeddings, 800/80 chunking, top-8 retrieval.

LLM agents3 projects
Proficiency76%

Structured output with explicit human-escalation branches.

OpenAI / Gemini4 projects
Proficiency74%

Ad-creative generation and grounded support responses.

LangChain1 project
Proficiency68%

Retrieval chain and output parsing inside the support agent.

Pabbly / AiSensy2 projects
Proficiency70%

Fee reminders and outbound messaging before the n8n migration.

AI & Automation Expertise

Focused on production automation, grounded agents and the systems they integrate with.

Workflow Automation

Technologies
n8nCronWebhooksGoogle Workspace
Key achievements
  • 49 workflows built, ten live on daily, scheduled and real-time triggers
  • Full LMS student lifecycle automated across 13 branches
  • Zero manual kick-off — every run is scheduled or event-driven

Retrieval-Grounded Agents

Technologies
QdrantGeminiLangChainStructured output
Key achievements
  • Answers constrained to retrieved passages, never invented
  • Explicit escalation flag routes refunds and complaints to a human
  • 800/80 chunking with top-8 retrieval over the brochure corpus

Systems Integration

Technologies
RESTOAuth 2.0Chrome extensionsWHMCS
Key achievements
  • Edmingle, Meritto CRM, MCube telephony and WHMCS wired together
  • Chrome extension feeding a webhook receiver with deduplication
  • Billing data piped into Sheets for revenue reporting

Operational Alerting

Technologies
MCube APIGoogle SheetsGmail
Key achievements
  • Role-specific call targets computed nightly and adjusted per walk-in
  • Only below-target agents emailed, with their manager copied
  • Replaced a manual nightly spreadsheet review entirely

Full-Stack Platforms

Technologies
Next.jsNestJSSupabaseBullMQ
Key achievements
  • Three-sided job marketplace live at job.skillcircle.in
  • Role-based admission platform with SLA timers and approval gates
  • Postgres schema designed across 30+ migrations

Hosting Infrastructure

Technologies
LinuxcPanel / WHMDNSBitNinja
Key achievements
  • 1,200+ active domains across shared and VPS environments
  • Downtime diagnosed and resolved to restore uptime
  • The layer everything else I build depends on
Questions

Common questions

Who is Shivam Gupta?

Shivam Gupta is an AI & Automation Engineer based in Noida, India. He builds production workflow automation, retrieval-grounded AI agents, and the full-stack platforms those systems feed. He started as a React JS Developer at SNVA Ventures in September 2024, then joined SkillCircle in February 2025 as an IT Executive managing hosting for 1,200+ domains, and moved into the AI & Automation Engineer role in January 2026 after the automations he built became core operations.

What does Shivam Gupta automate?

Shivam Gupta has built 49 workflows at SkillCircle, ten of them running in production — eight in n8n, the rest on other tooling. They cover the LMS student lifecycle across 13 branches — daily onboarding provisioning and scheduled archival — plus fee-reminder emails, real-time certificate generation and delivery, Canva seat approvals, and a nightly sales-performance alert that joins counsellor rosters, walk-in logs and live MCube telephony data. Every one runs on a schedule or a webhook with no manual start.

How does Shivam Gupta's RAG support agent work?

The agent answers inbound support queries from SkillCircle's brochure corpus. The documents are chunked at 800 tokens with 80 tokens of overlap into a Qdrant vector store using Gemini embeddings, and the top eight passages are retrieved per query. The model is constrained to answer only from those retrieved passages and returns a structured object containing both the reply and an escalation flag, so refunds, complaints and account-specific questions route to a human instead of receiving an invented answer.

What is Shivam Gupta's tech stack?

Shivam Gupta works primarily in n8n for workflow automation, with Qdrant, Gemini and LangChain for retrieval-grounded agents. On the application side he uses TypeScript with Next.js and NestJS, backed by Supabase and PostgreSQL, with Redis and BullMQ for queued work. He also runs the infrastructure underneath: Linux hosting, cPanel and WHM, DNS, SSL and Cloudflare across more than 1,200 domains.

How does Shivam Gupta approach building automation?

Shivam Gupta builds automation in three stages. First he traces the manual process end to end with whoever performs it today, including the steps nobody documented. Then he builds a read-only version, using diagnostic probes to confirm the data is shaped as expected while write operations stay disabled. Only once inputs are verified does he enable writes against a small slice, check the output by hand, then widen. Finished systems run unattended and report only exceptions.

Is Shivam Gupta available for hire?

Yes. Shivam Gupta is open to AI Engineer and AI & Automation Engineer roles, remote or in Delhi NCR. He can be contacted through the form at https://shivamg.in/contact, and his work is documented at https://shivamg.in/projects with architecture write-ups at https://shivamg.in/case-studies.

Ready to Build Something That Runs Itself?

Let’s talk about the manual work you’d rather not be doing next quarter.

Let’s Collaborate