AI Platform Engineer: Build & Scale Production LLM Pipelines

GigaBrands; Colombia; Presencial; COP 90.000.000 - 150.000.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Competitive salary

High-impact ownership

Opportunities to scale AI systems

Descripción de la vacante

GigaBrands is hiring an AI Full Stack Engineer to build and scale AI-powered infrastructure across the full stack. You’ll work at the intersection of AI and production systems, delivering scalable AI pipelines, dashboards, and observability.

The role focuses on reducing costs while improving performance and quality across the platform. You’ll develop end-to-end AI features, from inbound message classification to pre-call intelligence briefs, integrating with data sources and ensuring robust

Formación

• 3+ years of hands-on experience with TypeScript/Node.js in production
• Strong React skills with modern frontend architectures
• PostgreSQL query optimization, migrations, indexing
• Experience building and optimizing LLM-based pipelines (RAG)
• Ability to add observability, cost controls, and monitoring for AI systems
• Experience with REST/OAuth/webhooks integrations
• Familiarity with Linux server environments and deployments

Responsabilidades

• Build AI pipelines for client performance insights
• Improve RAG retrieval quality and data enrichment
• Add tool integrations for real-time data in LLM pipelines
• Debug classification errors in AI systems
• Optimize LLM costs and performance
• Build dashboards for AI metrics and usage
• Add observability to pipelines
• Expand content quality and lead qualification systems

Conocimientos

TypeScript/Node.js

React

PostgreSQL

API integrations

Linux server operations

Production LLMs

RAG systems

Cost and performance optimization

Herramientas

REST APIs

OAuth

Webhooks

Descripción del empleo

GigaBrands is hiring an AI Full Stack Engineer to build and scale AI-powered infrastructure across the full stack. You’ll work at the intersection of AI and production systems, delivering scalable AI pipelines, dashboards, and observability.

The role focuses on reducing costs while improving performance and quality across the platform. You’ll develop end-to-end AI features, from inbound message classification to pre-call intelligence briefs, integrating with data sources and ensuring robust