Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am Juan Jaramillo, a Generative AI Engineer with 6+ years of experience building production-grade AI systems that bridge research and enterprise deployment. My career spans computer vision and retail automation to multi-LLM orchestration and agent reasoning, and I’ve led initiatives that turn complex analyses into scalable, automated workflows. I specialize in end-to-end ML pipelines, RAG systems, agentic LLM architecture, and cloud-native infrastructure on AWS and GCP. I love translating business needs into reliable AI products, APIs, and automations that empower non-technical teams to deploy sophisticated LLM-powered workflows while delivering measurable business impact.…I am Juan Jaramillo, a Generative AI Engineer with 6+ years of experience building production-grade AI systems that bridge research and enterprise deployment. My career spans computer vision and retail automation to multi-LLM orchestration and agent reasoning, and I’ve led initiatives that turn complex analyses into scalable, automated workflows. I specialize in end-to-end ML pipelines, RAG systems, agentic LLM architecture, and cloud-native infrastructure on AWS and GCP. I love translating business needs into reliable AI products, APIs, and automations that empower non-technical teams to deploy sophisticated LLM-powered workflows while delivering measurable business impact.

Juan Jaramillo

AI Engineer, Back-End Developer, AI Developer, +4





I am Juan Jaramillo, a Generative AI Engineer with 6+ years of experience building production-grade AI systems that bridge research and enterprise deployment. My career spans computer vision and retail automation to multi-LLM orchestration and agent reasoning, and I’ve led initiatives that turn complex analyses into scalable, automated workflows. I specialize in end-to-end ML pipelines, RAG systems, agentic LLM architecture, and cloud-native infrastructure on AWS and GCP. I love translating business needs into reliable AI products, APIs, and automations that empower non-technical teams to deploy sophisticated LLM-powered workflows while delivering measurable business impact.…I am Juan Jaramillo, a Generative AI Engineer with 6+ years of experience building production-grade AI systems that bridge research and enterprise deployment. My career spans computer vision and retail automation to multi-LLM orchestration and agent reasoning, and I’ve led initiatives that turn complex analyses into scalable, automated workflows. I specialize in end-to-end ML pipelines, RAG systems, agentic LLM architecture, and cloud-native infrastructure on AWS and GCP. I love translating business needs into reliable AI products, APIs, and automations that empower non-technical teams to deploy sophisticated LLM-powered workflows while delivering measurable business impact.

Available to hire

I am Juan Jaramillo, a Generative AI Engineer with 6+ years of experience building production-grade AI systems that bridge research and enterprise deployment. My career spans computer vision and retail automation to multi-LLM orchestration and agent reasoning, and I’ve led initiatives that turn complex analyses into scalable, automated workflows.

I specialize in end-to-end ML pipelines, RAG systems, agentic LLM architecture, and cloud-native infrastructure on AWS and GCP. I love translating business needs into reliable AI products, APIs, and automations that empower non-technical teams to deploy sophisticated LLM-powered workflows while delivering measurable business impact.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

Spanish; Castilian

Fluent

English

Advanced

Work Experience

Technical Lead (AI Automation & Integration) at White Horse AI

March 1, 2026 - Present

Led end-to-end implementation of the OpenClaw coordination framework and multi-tool AI automations for 15 enterprise clients, reducing operational workload by up to 30% and achieving 87% post-deployment engagement within one month. Architected a click-and-deploy LLM framework enabling non-technical teams to configure sophisticated AI agents without coding; built automations including an Instagram compliance scraper (30+ accounts, 20-minute tracking vs. 4+ hours manual) and an AI-powered quoting engine with image/audio analysis. Designed an n8n + AWS integration ecosystem covering lead routing, automated invoicing (CRM/Xero), calendar sync, and client-specific sales bots; established governance by data sensitivity and automated issue resolution pipelines. Mentored technical team members and clients on AI system architecture, operationalization, and scalable deployment patterns.

AI Engineer at Synthion AI

December 1, 2024 - December 1, 2025

Developed core AI agent for a wearable personal assistant: a multi-LLM orchestration layer (OpenAI, Gemini, DeepSeek) with conversational reasoning and task execution across diverse device contexts. Built a RAG system with persistent memory for conversation history, user preferences, and contextual information; integrated multimodal capabilities for image analysis and environmental question-answering. Integrated external services (Gmail, Outlook, image recognition APIs) enabling real-world agent actions, including sending messages, retrieving user information, and contextual decision-making. Deployed scalable serverless AI services (Azure Functions) enabling low-latency communication between wearable hardware and cloud-based inference systems.

Backend Engineer→Tech Lead at Lucro

February 1, 2021 - December 1, 2024

Designed and deployed scalable backend systems and an end-to-end computer vision pipeline where sales reps captured refrigerator images and AI models detected product presence, stock-outs, and share-of-shelf metrics. Implemented object detection and classification models (YOLO, CNNs) generating automated order recommendations, increasing product rotation and driving 23% sales uplift. Built WhatsApp automation bots and large-scale web scraping pipelines enabling retailers to manage campaigns, generate reports/PDFs, and track competitive pricing and promotional trends across retail chains. Led a team of 5 engineers as Tech Lead, overseeing system architecture, backend scalability (FastAPI, AWS, GCP), code reviews, and technical mentoring across a distributed team.

Assistant Professor at Universidad de los Andes

July 1, 2020 - June 1, 2024

Taught undergraduate courses in Machine Learning, Deep Learning, and Applied Data Science with hands-on projects covering neural networks, computer vision, NLP, and reinforcement learning. Designed and supervised end-to-end ML pipelines where students built models from data preprocessing through evaluation and deployment, gaining production-grade experience. Mentored student research projects and contributed to curriculum development emphasizing practical applications and model evaluation best practices.