AI Engineer — Advanced RAG & Multi-Agent Systems.
17 years enterprise B2B ops · Production-first
All public, all auditable, no toy projects
ACC Ltd · Lafarge · MP Birla Group — AGM level
Speech → structured CRM schema, Zoya Agent
Distribution DB architecture, enterprise scale
The Moat
Not a researcher with no deployment depth. Not a developer with no domain context. Both — fused.
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.
19+ public repos: stateful agentic graphs, custom MCP integrations, stealth automation, voice pipelines, optimized for resource-constrained 8GB hosts, scaled to production workloads. All publicly auditable at dhrubo.shop.
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.
Technical Stack
Selected Production Projects
True MCP abstraction layer — RAG, GitHub, Filesystem, Browser, Voice, Postgres as discoverable, auditable, executable tools via stdio/SSE JSON-RPC.
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.
High-evasion crawler with browser fingerprint spoofing bypassing Cloudflare/Imperva. Custom SMTP handshake engine validates mailboxes via MX records before transmission.
Multi-agent RAG network analyzing competitor price sheets, hybrid vector retrieval, feeding live context into negotiation systems in real time.
Real-time rebate evaluation logic at the database level, not application layer. Eliminated multi-million dollar RevOps audit leakage.
GitHub · dhruboshop
Every line of code is public. No toy projects. Real architecture decisions on every commit.
Latest build, advanced AI operations system
MCP abstraction layer
AI signal processing and intelligence stack
Agentic reasoning, stateful graph evaluation
Vapi + Claude 3.5 Realtime
LangGraph RevOps multi-agent system
Hybrid RAG, competitor pricing
DB-tier rebate evaluation
AI-native CRM platform, Next.js 15
Experience
Open To
Designing production agentic systems. Multi-agent orchestration, MCP integration, stateful graph design, observability-first architecture.
Taking AI from prototype to production. RAG systems, voice pipelines, automation infrastructure. Real deployment, not research.
Building the infrastructure layer for AI products. Tool registries, evaluation pipelines, memory systems, observability backends.
Early-stage AI-native products where domain depth matters. B2B, enterprise, supply chain, RevOps — 17 years of real-world context.
Contact
For detailed project discussions, enterprise AI systems, founding engineer roles, and formal business inquiries.
Send EmailDirect line for availability discussions, project scoping, and technical conversations. IST timezone — Kolkata, India.
WhatsApp