MONTANO
Jaren Montano
Generative AI Developer
Custom Solutions & AI Automations
Professional Path
August 2025 — Present
ATI of America
AI Developer
Built AI-driven automations that improved after-hours support, auto-generating tickets and escalating urgent issues, reducing on-call workload and improving response times.
Contributed to the development of internal automation tools that save ~20 hours per project, including automated documentation, BTU calculations, and I/O sheet generation.
Designed and developed a scope-of-work validation tool that enforces required design inputs, ensures data consistency, and significantly reduces design rework and back-and-forth.
Contributed to a full-stack SaaS web application for AV industry workflows spanning CRM, project delivery, and service operations.
Implemented workflow automation using n8n, Zapier, and multiple LLMs (GPT, Claude, Gemini).
Supported cloud deployment and scalability using AWS.
July 2024 — August 2025
Sapphirus Systems
Generative AI/ML Engineer
Design and deploy end-to-end machine learning and AI systems, from data ingestion and training to production deployment
Build Retrieval-Augmented Generation (RAG) pipelines for real-world NLP and automation use cases.
Develop and integrate model-serving and orchestration infrastructure using PyTorch, TensorFlow, and scikit-learn.
Create custom algorithms and scalable models optimized for performance, reliability, and maintainability.
Architect cloud-native AI solutions on Azure, with a focus on scalability and production readiness
Collaborate across product and engineering teams to translate business requirements into production-ready AI systems.
FEATURED
WORK
Professional Projects
Rack Builder
Drag-and-drop interface for building 2-post rack layouts. Connects to projects, manages wire layouts, and auto-generates IO sheets for design, Rack Build and Technicians teams.
AI Helpdesk Automation
Zapier workflow that screens after-hours helpdesk emails. Automatically creates tickets for urgent equipment failures and sends push notifications to on-call technicians.
CRM-to-PM Sync
Automated workflow that synchronizes new clients across CRM, project management, and service software with consistent naming conventions.
Question Generator RAG
Full-stack RAG application generating high-quality Q&A using Azure OpenAI. Features feedback refinement loops and LLM Lingua for token optimization.
Prediction Center ML
Hybrid prediction system combining Decision Tree Regression with RAG for student score predictions. Includes Azure OpenAI fallback and continuous model retraining.
MCP Server for LLM Agents
Converted existing LangChain/LangGraph tools to MCP protocol via Flask. Added OAuth security layer enabling any LLM or agent to connect seamlessly while maintaining security.
SOFTWARE
PROFICIENCY
Generative AI
Tap to view
Generative AI
- RAG Pipelines
- Model Training
- PyTorch / TensorFlow
- Vector Databases
- Unstructured Data
Full Stack
Tap to view
Full Stack
- Python (Flask)
- React / Node.js
- JavaScript / Java
- SQL / NoSQL
- REST APIs
Cloud
Tap to view
Cloud
- Azure ML / Functions
- Azure Blob Storage
- AWS S3 / RDS
- Git / GitHub
Automation
Tap to view
Automation
- N8N Workflows
- Zapier Integrations
- Python Scripts
- Process Optimization
BACHELOR OF SCIENCE IN COMPUTER SCIENCE
Weber State University, Ogden, UT
CONTACT
Professional Inquiries Only