JAMES MONTOYA
Data & AI Builder | LLM Pipelines, Workflow Automation & Production AI Systems
Sydney, Australia | jamonhin@gmail.com | LinkedIn: /in/jamesmontoya
Professional Summary
I build things that ship. Sydney-based AI Engineer with 15+ years spanning enterprise data engineering, LLM-powered automation, and production AI systems. I use AI-native tooling every day — not as a party trick, but as a genuine productivity multiplier. My weekend projects become working demos; my curiosity drives me to experiment with every new framework, model, and tool the moment it drops. Core stack: n8n (self-hosted, production-grade), Python, SQL, ArangoDB, AWS, Docker. Track record of reducing manual processes by up to 95% and delivering end-to-end solutions from idea to live production in days, not months. Deep experience in regulated industries including financial services, defence recruitment, not-for-profit, banking and telecommunication.
Show, Don't Tell — Featured Work
Voice of the Customer Analytics Platform (built as a weekend POC)
  • End-to-end pipeline: real insurance call transcripts → LLM extraction (Gemini 2.5 Flash) → ArangoDB storage → live webhook dashboard
  • 16-field structured extraction: calibrated sentiment scoring, sentiment journey tracking, churn risk, topic classification, agent performance
  • Benchmarked GPT-4.1 Mini vs Gemini 2.5 Flash on identical transcripts — selected Flash for superior nuanced sentiment detection
  • Video walkthrough: https://youtu.be/aUAvT4RlgSw
  • Live dashboard: https://automation.ethicalaispecialists.com.au/webhook/voc-dashboard
  • Full project portfolio: https://jamonhin.github.io
Professional Experience
AI Engineer — RAG System & Document Intelligence
Nov 2025 — Present
Consultant for eThink Solutions
Brisbane (Remote), Australia
  • Building a RAG (Retrieval-Augmented Generation) system enhancing eThink's custom-built mortgage broker CRM with document intelligence capability
  • Processing 150+ loan documents with 95%+ accuracy using Claude (Anthropic API) as the LLM layer
  • Designed ArangoDB multi-model schema combining document store, graph database, and vector search for document classification, chunk-level tagging, and relationship mapping between banks, processes, and compliance requirements
  • Reduced manual document lookup time by 80% through natural language conversational interface
  • Built document classification admin interface with graph visualisation of document relationships
  • Tech stack: n8n, ArangoDB, Claude API, AWS (EC2, S3), Docker, Traefik
AI Engineer - Workflow Automation & AI Integration
Jun 2025 - Present
Consultant for Defence & Government Recruitment Firm
Canberra (Remote), Australia
  • Built multi-stage AI recruitment pipeline: CV ingestion, structured data extraction (skills, security clearances, capability domains), and graph-based storage in ArangoDB
  • Designed multi-agent architecture (Router → Query Builder → Response Formatter → Validator) orchestrated through n8n for intelligent candidate matching
  • Integrated conversational AI agent into Microsoft Teams enabling recruiters to find candidates through natural language queries
  • Developed HubSpot integration processing ~1,759 contacts with AGSVA clearance and skills data
  • Built automated resume processing pipeline reducing manual data entry by 95%
  • Engineered dual-layer skill extraction system preventing domain mismatches with 90%+ accuracy
AI Consultant - AI Training & Workflow Automation
Nov 2024 — Present
Consultant For Mary Mackillop Today
Sydney, Australia
  • Created and developed AI Training Video Course for Not-for-Profit Organisation
  • Developed AI-powered automation systems using N8N
  • AI advice and consulting
  • Automation for managing the end-to-end lead data pipeline for Meta digital acquisition campaigns
AI & Data Engineer — Independent Projects
Nov 2023 - Nov 2024
Ethical AI Specialists (Independent Practice)
Sydney, Australia
  • Built production-ready RAG chatbot with PostgreSQL/pgvector, Next.js 15, React, and Redis
  • Developed Jobseeker multi-agent system using LangChain, CrewAI, and OpenAI
  • Developed Docker-based ML environments for scalable model development and deployment
  • Built predictive models for nonprofit donor behaviour analysis using clustering algorithms
  • Implemented automated ETL processes using Apache Airflow for ML data pipelines
  • Designed and prototyped AI-powered automation workflows using n8n and LLM APIs
  • Completed Master of Software Engineering (AI Specialisation) at Torrens University
  • Stack: Python, PostgreSQL, pgvector, Supabase, Next.js, React, TypeScript, Redis, Docker, Apache Airflow
Data Engineer & Business Intelligence Developer
2014 - 2017
Tigo (Telecommunications)
Colombia
  • Developed mobile KPI dashboard application using Apache PhoneGap, including interface design for executive users
  • Created ETL packages in SSIS for seamless multi-source data integration
  • Automated reporting systems using SQL Server, reducing manual effort by 80%
  • Implemented data scraping and processing solutions with Python
  • Designed real-time data visualization systems using QlikView for executive decision-making
  • Stack: SQL Server, SSIS, Python, QlikView, Apache PhoneGap, VBA
Analyst Developer & Database Specialist
2006 - 2014
Grupo Bancolombia (Financial Services)
Colombia
  • Led treasury database reporting migration in a regulated banking environment, ensuring audit compliance and seamless transition
  • Developed Java applications for Murex financial system integration and data processing
  • Implemented reporting solutions using Datamart and SAP Business Objects
  • Managed Murex system transition, optimizing financial data processes and system integration
  • Created VBA macros automating spreadsheet-to-production migrations
  • Leveraged Oracle Database and Business Objects for stakeholder reporting
  • Stack: Oracle, SQL, Java (Murex), VBA, SSIS, SAP Business Objects, Datamart, Murex
Featured Projects
AI-Powered Mortgage Broker Document Assistant
2025
n8n, ArangoDB, Claude API, AWS EC2, Docker, RAG
RAG system for eThink Solutions' mortgage broker CRM enabling staff to query 150+ loan documents through natural language. Multi-model database architecture combining document store, graph, and vector search with 95%+ accuracy and 80% reduction in manual lookup time.
Jobseeker Multi-Agent System
Jan 2025
Python, LangChain, CrewAI, OpenAI, React
Developed intelligent job application system analyzing postings and generating tailored cover letters and optimized resumes using multi-agent AI architecture.
Automated Resume Processing & CRM Integration
Jul 2025
n8n, ArangoDB, Claude API, HubSpot, Microsoft Teams, Python
Multi-stage AI recruitment pipeline for Defence & Government recruitment firm. CV ingestion, structured data extraction, ArangoDB graph storage, and Microsoft Teams chatbot with multi-agent architecture. Reduced manual data entry by 95%.
Cleaning Company Management System
May 2025
PostgreSQL, N8N, OpenAI GPT, Docker
Multi-agent system automating operations and providing actionable insights for cleaning service providers with 30+ interrelated database tables.
ML-Powered Donor Analysis System
2023-2024
Docker, Python, Apache Airflow, Scikit-Learn, KMeans
Comprehensive system analyzing donor behavior and predicting contributions for nonprofit organizations using containerized ML environments.
Technical Skills
AI & LLM Integration
Claude (Anthropic API), OpenAI, Gemini, Grok, Ollama, Amazon Bedrock, Prompt Engineering, Multi-Agent Orchestration, RAG Systems
Frameworks & Orchestration
n8n (self-hosted, production-grade), CrewAI, LangChain, LlamaIndex
Programming
Python, TypeScript, JavaScript, SQL, Node.js, React.js, Java, VBA
Databases
ArangoDB (document, graph, vector search), PostgreSQL, pgvector, Supabase, SQL Server, Oracle, MySQL
Cloud & Infrastructure
AWS (EC2, S3, Bedrock), Docker, Traefik, Nginx, Let's Encrypt, Azure (Outlook, Teams, SharePoint, OneDrive APIs), Google Cloud (API connections), Serverless Architectures
Integration & APIs
HubSpot, Salesforce, Azure, Google APIs, any system with API connectivity
Data Engineering
ETL Pipelines (SSIS, Airflow, n8n) | Data Modelling | Datamart | MLOps | Multi-source integration
Frontend & Dashboards
React.js | Next.js | Chart.js | Webhook-served dashboards | Power BI | Tableau | PhoneGap (mobile apps) | HTML | JavaScript
Analytics & Visualisation
Tableau, Power BI, QlikView, Machine Learning, Scikit-Learn
Education
Master of Software Engineering (AI Specialization)
2021 - 2024
Torrens University Australia
Sydney, Australia
Advanced studies in machine learning, artificial intelligence, and software development with focus on practical AI applications.
Specialization in Software Development
2013
Universidad de Medellín
Colombia
Software development lifecycle, Scrum methodologies, requirements elicitation, and software engineering best practices.
Bachelor of Computer Science
2009
Politécnico Jaime Isaza Cadavid
Colombia
Foundation in computer science, programming, databases, and software development principles.
Key Achievements
  • Built Voice of the Customer POC in days — end-to-end pipeline processing real insurance call transcripts with live dashboard
  • Reduced manual document lookup time by 80% through RAG system implementation
  • Reduced manual data entry by 95% through AI-powered automation pipelines
  • Achieved 95%+ accuracy in intelligent document processing across 150+ documents
  • Designed multi-agent AI architectures for production enterprise environments
  • Successfully migrated complex financial database systems at enterprise scale
  • Delivered AI training programs for not-for-profit organisations
Core Competencies
  • LLM Pipeline Design & Deployment
  • Multi-Agent AI Architecture
  • RAG System Implementation
  • Workflow Orchestration (n8n)
  • Graph Database Design (ArangoDB)
  • Enterprise Data Integration
  • Business Process Automation
  • Cross-functional Stakeholder Communication