AI Automation Engineer

Intelligent Workflow Automation That Eliminates Manual Friction

I build autonomous n8n workflows, WhatsApp business bots, CRM synchronizations, and AI-powered background processing pipelines.

AI Agentsn8nAPIsWhatsAppVoice

Technical Skills

What I bring as a Automation engineer

Workflow Orchestration

n8n— Visual workflow automation platform
Custom Webhooks— Idempotent event handlers
BullMQ— Background job scheduling
Cron & Triggers— Time-based automation

Messaging & Communication

WhatsApp Cloud API— Business messaging automation
Voice Transcription— Audio-to-text processing
Slack / Discord— Notification integrations
Email Automation— Template-driven campaigns

AI Processing

LLM Classification— Intent & sentiment analysis
Document Extraction— PDF/invoice data parsing
Lead Qualification— Automated scoring & routing
RAG Chatbots— Knowledge-base Q&A bots

Integration Layer

REST APIs— Third-party system connectors
CRM Sync— Multi-system data pipelines
LemonSqueezy / Stripe— Payment event processing
PostgreSQL / Redis— State & queue persistence

Architecture

How I architect automation systems

01

Trigger Detection

Webhook receivers, cron schedules, or message events initiate the automation pipeline.

02

Data Extraction

Parse incoming data — messages, documents, voice notes — into structured formats for processing.

03

AI Processing

Route through LLM classification, intent extraction, or document analysis based on the data type.

04

Action Execution

Push results to CRMs, send WhatsApp responses, trigger Slack notifications, or update databases.

05

Monitoring & Retry

Log every step, handle failures gracefully with BullMQ retries, and alert on anomalies.

Featured Work

Production projects as a Automation engineer

Gen AI & VoiceLive in Production

Kookabe AI Suite

Enterprise WhatsApp RAG Chatbot & Automated AI Voice Mail

Problem

Companies received hundreds of repetitive WhatsApp voice notes, PDFs, and product inquiries daily, resulting in 4-8 hour response delays and missed sales leads.

Solution

Built a hybrid RAG system with pgvector and Claude 3.7 that parses customer inquiries, searches internal PDF documentation, and generates accurate answers with human-handoff triggers.

Architecture

  • WhatsApp Business API webhooks ingesting incoming text, voice notes, and document files
  • Hybrid RAG combining pgvector dense embeddings with BM25 keyword reranking
  • FastAPI backend handling asynchronous LLM streaming and conversation state
  • Automated audio transcription pipeline extracting lead data directly into CRM webhooks

Verified Results

Automated over 90% of routine inquiries with sub-3-second first responsesZero hallucinations verified via strict citation and source-chunk verificationContinuous 24/7 uptime handling high-volume customer messages
LangChainClaude 3.7FastAPIPostgreSQL / pgvectorWhatsApp Cloud APIRedis
View Live

Experience

Where I've applied these skills

AI & Full-Stack Engineer

atUpworkTop Rated

May 2026 — Present

Delivering production AI workflows, full-stack Next.js/NestJS platforms, and cloud DevOps systems for high-growth tech startups and international clients.

  • Consulting on AI agent architecture, hybrid RAG pipelines, and conversational voice systems.
  • Building scalable REST APIs, microservices, and database schemas with PostgreSQL and Prisma.
  • Maintaining a 100% Job Success Score with verified 5-star client contracts.
AI AgentsLangChainClaude 3.7Next.jsNestJSPostgreSQLDocker

Process

How I work

01

Process Mapping

Document the current manual workflow, identify bottlenecks, and define automation triggers.

02

Pipeline Design

Architect the data flow — triggers, transformations, AI processing, and output destinations.

03

Build & Test

Implement with proper error handling, retries, idempotency, and end-to-end testing.

04

Deploy & Monitor

Ship to production with logging, alerting, and dashboards to track automation health.

FAQ

Frequently asked questions

What kind of business processes can you automate?

Lead qualification, customer inquiry routing, document data extraction, multi-system CRM synchronization, WhatsApp business messaging, scheduled reporting, and payment event processing.

Do you use n8n or custom code?

Both. I use n8n for visual workflow orchestration with custom code nodes for complex logic. For high-performance or real-time requirements, I build custom webhook microservices with Node.js and BullMQ.

Can you build WhatsApp bots?

Yes. I've built enterprise WhatsApp systems with the official Cloud API — handling text, voice notes, documents, and media with AI-powered responses and human-handoff triggers.

How do you handle failures in automated workflows?

Idempotent webhook handlers with cryptographic signature verification, BullMQ retry queues with exponential backoff, dead-letter queues for unprocessable messages, and real-time error notifications.

Need to automate a business process?

From WhatsApp bots to multi-system workflows — I build automation that eliminates manual friction with AI intelligence.