Available · Remote / Async · IST · Immediate

AI Systems Builder

Dhrubojyoti Gangopadhyay · Dhrubo

AI agent systems that survive production.

Q: Who is Dhrubo?

Dhrubo is Dhrubojyoti Gangopadhyay, a production AI agent systems builder based in Kolkata, India with 17 years of enterprise B2B operations experience and 31 public AI systems.

Q: What does Dhrubo build?

Dhrubo builds production AI agents, advanced RAG systems, LangGraph multi-agent orchestration, MCP tool registries, voice AI pipelines, compliance intelligence, CRM automation, and database-tier business logic.

Q: What roles is Dhrubo open to?

Dhrubo is open to AI Systems Architect, Applied AI Engineer, AI Platform Engineer, and Founding Engineer roles, especially remote or async B2B AI work.

Q: How can I contact Dhrubo?

Email Dhrubo at dhrubo@dhrubo.shop or WhatsApp/call +91 82408 01921.

Advanced RAG, MCP tooling, LangGraph orchestration, voice AI, and DB-tier logic for enterprise workflows.

17 years enterprise B2B operations fused with public, auditable AI engineering.

Get In Touch GitHub

LangGraphMCPVapi Voice AIPlaywright StealthFastAPIPostgreSQLn8nNext.js 15

Agent orchestration cockpitLIVE

Supervisor

MCP tool fabricLangGraph supervisorHybrid RAG memoryVoice CRM parserAudit-grade traces

route.intent = enterprise_rag

voice.schema_latency < 250ms

tool.calls = auditable

Public AI Systems

Agentic workflows, RAG, compliance, voice, CRM, outreach

17yr

Enterprise Experience

ACC Ltd · Lafarge · MP Birla Group — AGM level

<250ms

Voice Pipeline Latency

Speech → structured CRM schema, Zoya Agent

40%

Decision Latency Reduced

Distribution DB architecture, enterprise scale

Why Dhrubo Is Different

He does not just wrap APIs. He designs agent operating systems.

Most AI portfolios stop at demos. Dhrubo’s work is built around the hard parts: tool discovery, memory routing, fallback loops, voice latency, DB-tier rules, audit trails, and deployment on constrained infrastructure.

Production-first Database-tier logic Multi-agent control

Answer Engine Brief

Clear answers. No fluff.

For Google, recruiters, founders, and AI answer engines: the direct version of what Dhrubo does and why it matters.

Who is Dhrubo?

Dhrubo is Dhrubojyoti Gangopadhyay, a production AI agent systems builder based in Kolkata, India with 17 years of enterprise B2B operations experience and 31 public AI systems.

What does Dhrubo build?

Dhrubo builds production AI agents, advanced RAG systems, LangGraph multi-agent orchestration, MCP tool registries, voice AI pipelines, compliance intelligence, CRM automation, and database-tier business logic.

What roles is Dhrubo open to?

Dhrubo is open to AI Systems Architect, Applied AI Engineer, AI Platform Engineer, and Founding Engineer roles, especially remote or async B2B AI work.

How can I contact Dhrubo?

Email Dhrubo at dhrubo@dhrubo.shop or WhatsApp/call +91 82408 01921.

Signature System

Agent OS Lab

Watch the operating model: retrieve context, route tools, execute safely, and leave an audit trail. This is the difference between a chatbot and an enterprise agent system.

AGENT OSDHRUBO

Sense

Hybrid RAG + domain memory

Route

LangGraph supervisor + MCP registry

Act

Voice, browser, database, CRM tools

Audit

Telemetry, traces, schema outputs

$ supervisor.route(intent)

→ mcp.tools.discover()

✓ action.output.schema_validated

The Moat

Enterprise ops meets production AI.

Not a researcher with no deployment depth. Not a developer with no domain context. Both — fused.

17yr Enterprise B2B Operations (AGM level)40% decision latency reduction22% supply gap reduction+14% YoY market share scaled

Supply chain + pricing → AI architecture

17 years managing supply chains, pricing frameworks, dealer rebate architecture, RevOps leakage at national scale across India's largest industrial conglomerates, baked into every retrieval architecture and agent guardrail.

ACC Ltd.LafargeMP Birla GroupAGM/Senior Manager

Production systems, not prototypes

31 public repos: stateful agentic graphs, custom MCP integrations, stealth automation, voice pipelines, compliance systems, multilingual support agents, and production workloads. All publicly auditable at dhrubo.shop.

LangGraphMCP stdio/SSEVapiPlaywright Stealth

Database-tier thinking

Real-time rebate evaluation logic at the database level, not application layer. Translating multi-state commercial ops into database schemas — a rarely found skillset in AI engineers.

PL/pgSQLPostgreSQLSupabaseERP Schema Design

Technical Stack

Systems vocabulary, production grammar.

Agentic & Graph

LangGraph (Supervisor Routing)
Parent-Doc Memory Checkpointing
LCEL/Dynamic Fallback Loops
Self-Correcting Agents
Multi-Agent Orchestration

RAG & Protocols

MCP (stdio/SSE JSON-RPC)
Hybrid BM25 + Vector Search
Reciprocal Rank Fusion (RRF)
Parent-Child Chunking
ChromaDB/Context Compression

Voice & Realtime

Vapi (Conversational Voice AI)
WebSockets (FastAPI & Node.js)
Claude 3.5 Realtime API
Async Voice-to-JSON Orchestration
Structured Telemetry Parsing

Web Automation

Playwright Stealth
Fingerprint Evasion (fake-useragent)
Anti-Bot Bypass (Cloudflare/Imperva)
HTML→JSON Schema Extraction
SQLite State Persistence

Databases & Backend

PostgreSQL (PL/pgSQL Stored Procs)
Supabase/SQLite WAL
FastAPI/Docker/GCP/Render
n8n Workflow Automation
Redis/Google Sheets API

Frontend & LLMs

Next.js 15/TypeScript/React
Tailwind CSS
OpenAI GPT-4o/Gemini Embeddings
Anthropic Claude 3.5
Groq Llama 3

Selected Production Projects

Seven systems that prove the claim.

ComplianceGraph — Agentic Compliance Intelligence

Graph-minded compliance system for tracing obligations, controls, evidence, and reasoning paths instead of treating compliance as flat document search.

PythonKnowledge GraphCompliance AIAgentic ReasoningAudit Trails

Architecture: compliance entity graph → retrieval layer → reasoning agent → evidence-backed answer path
Positioning: built for regulated workflows where traceability matters as much as answer quality
Why it matters: shows Dhrubo can translate business risk into AI system architecture

View Repository

SENTRA-AI — Operational Agent System

Current-generation AI operations build focused on agentic execution, workflow orchestration, and practical system behavior rather than static chat.

PythonAgentic WorkflowsAutomationSystem BuilderOps AI

Architecture: task intake → agent plan → workflow execution → telemetry-ready outputs
Signal: newest public build in the portfolio, showing active production momentum
Constraint: designed for practical operators, not just prompt demos

View Repository

NEXUS Enterprise AI Operations Platform

True MCP abstraction layer — RAG, GitHub, Filesystem, Browser, Voice, Postgres as discoverable, auditable, executable tools via stdio/SSE JSON-RPC.

PythonLangGraphMCPNext.js 15DockerGemini Embeddings

Architecture: Stateful LangGraph supervisor → MCP tool registry → dynamic routing → parent-doc memory checkpointing → audit logs
Key challenge: Every capability discoverable + auditable, prevent infinite agent cycles, 8GB RAM deployment
Constraint: Gemini embeddings + lazy-loaded Playwright for resource-constrained hosts

View Repository

Zoya Voice CRM Integration Agent

⚡ <250ms · Speech → Typed CRM Schema · Production

Orchestrates Vapi to manage WebRTC/SIP telephony, bypassing raw audio socket streams. Parses speech → structured CRM schemas at sub-250ms latency under concurrent high-throughput load.

VapiWebSocketsClaude 3.5 RealtimeFastAPISupabase

Latency: <250ms speech-to-structured CRM schema, zero UI-blocking
Reliability: Supabase direct write + enterprise webhook triggers with full telemetry logging
Concurrency: handles high-throughput inbound calls without blocking

View Repository

Vayu OS — High-Evasion AI Outreach Pipeline

High-evasion crawler with browser fingerprint spoofing bypassing Cloudflare/Imperva. Custom SMTP handshake engine validates mailboxes via MX records before transmission.

PythonPlaywright StealthGroqSQLiteGoogle Sheets API

Anti-bot bypass: Playwright Stealth + fake-useragent fingerprint spoofing
Email validation: direct SMTP MX-record handshake, zero bounce-backs
Crash resilience: SQLite transactional state manager, self-healing restarts

View Repository

B2B Sales Intelligence RAG

Multi-agent RAG network analyzing competitor price sheets, hybrid vector retrieval, feeding live context into negotiation systems in real time.

PythonLangGraphHybrid RAGFastAPIMIT License

Domain depth: 17yr enterprise pricing + distribution expertise encoded in retrieval architecture
Search method: Hybrid BM25 + vector search with Reciprocal Rank Fusion
Routing: LangGraph multi-agent routing for real-time negotiation context

View Repository

Dealer Rebate Intelligence System

Real-time rebate evaluation logic at the database level, not application layer. Eliminated multi-million dollar RevOps audit leakage.

PL/pgSQLPostgreSQL

Architecture choice: DB-tier logic vs application layer
Business outcome: multi-million dollar RevOps audit leakage eliminated
Domain basis: 10+ years managing national distributor networks

View Repository

GitHub · dhruboshop

31 repos. Active AI systems, not portfolio filler.

Every public build is evidence: agents, RAG, compliance intelligence, CRM, support automation, observability, and DB-tier logic.

31 Public ReposLatest builds updated this weekAI systems across Python, TypeScript, PL/pgSQL

Python3 days ago

Multilingual-Customer-Support-System

Multilingual AI support workflow

Python4 days ago

SENTRA-AI-

Operational agent system

Python5 days ago

ComplianceGraph

Compliance graph intelligence

TypeScript3 weeks ago

ValidateX

Validation-focused AI product surface

Python3 weeks ago

The-Salesman-Of-The-year-

AI sales agent system

PythonJun 5

EDITH

Advanced AI operations system

PythonMay 30

NEXUS-Enterprise-AI-Platform

MCP abstraction layer

PythonMay 30

signalstack-ai

AI signal processing and intelligence stack

PythonMay 28

nexus-os-RAG-LangGraph

RAG + LangGraph operating layer

PythonMay 28

realtime-fraud-detection-agent

Agentic reasoning, stateful graph evaluation

Python/MITMay 26

Enterprise-AI-Evaluation-and-Observability-Dashboard

Evaluation and observability dashboard

Python/MITMay 26

Multi-Agent-Revenue-Operations-Orchestrator-using-LangGraph

LangGraph RevOps multi-agent system

Python/MITMay 26

b2b-sales-intelligence-rag

Hybrid RAG, competitor pricing

AI VoiceMay 23

Zoya-Voice-Agent

Vapi + Claude realtime voice CRM

PL/pgSQLMay 22

loyalty_intelligence_system

DB-tier rebate evaluation

PythonMay 21

Vayu_AI_Outreach_Pipeline

AI outreach pipeline

TypeScriptMay 20

AI-native-CRM-platform-by-Dhrubo.Shop

AI-native CRM platform

View All 31 Repositories on GitHub

Experience

Enterprise field depth, AI shipping velocity.

Jan 2025 — Present

Self-Employed · Remote

Independent AI Engineer

Shipped 31 public AI systems — stateful graphs, advanced RAG networks, custom agent tracing backends, low-latency API wrappers, compliance intelligence, and agentic workflows
Built Zoya Voice Intake Agent: Vapi + WebRTC/SIP → structured CRM schema at <250ms under load
Engineered NEXUS — full MCP abstraction layer, discoverable/auditable tool registry via stdio/SSE
Designed B2B RAG networks with LangGraph multi-agent routing for real-time negotiation context
Built high-evasion Playwright crawler bypassing Cloudflare/Imperva with SMTP MX validation

LangGraphMCPVapiFastAPIPostgreSQLPlaywright StealthSupabase

2007 — 2024

ACC Ltd · Lafarge · MP Birla Group

AGM & Senior Manager — Revenue Operations

Directed commercial operations, designed distribution databases — reduced decision latency 40%
Architected incentive frameworks and distributor analytics — minimized supply gaps 22%, scaled market share +14% YoY
Translated multi-state commercial operations into database schema rules and ERP specs
Built national dealer rebate systems at DB tier — eliminated multi-million dollar RevOps leakage

Supply ChainRevOpsPricing FrameworksDistribution DBERP Specs

2005 — 2007

University of Kalyani

MBA — First Class

Specialization in Operations Management & Marketing Strategy

Operations ManagementMarketing Strategy

Open To

Bring him where agents need to become infrastructure.

AI Systems Architect

Designing production agentic systems. Multi-agent orchestration, MCP integration, stateful graph design, observability-first architecture.

Applied AI Engineer

Taking AI from prototype to production. RAG systems, voice pipelines, automation infrastructure. Real deployment, not research.

AI Platform Engineer

Building the infrastructure layer for AI products. Tool registries, evaluation pipelines, memory systems, observability backends.

Founding Engineer

Early-stage AI-native products where domain depth matters. B2B, enterprise, supply chain, RevOps — 17 years of real-world context.

Contact

Let's build something real.

dhrubo@dhrubo.shop

For detailed project discussions, enterprise AI systems, founding engineer roles, and formal business inquiries.

Send Email

+91 82408 01921

Direct line for availability discussions, project scoping, and technical conversations. IST timezone — Kolkata, India.