AI Engineer (LLMs)

TL;DR

AI Engineer (LLMs): Designing, developing, and deploying AI-driven features within real-world applications with an accent on LLM integration and production-grade backend services. Focus on building scalable RAG systems, agent frameworks, and optimizing LLM workflows for real-world products.

Location: Must be based in Colombia (only)

Company

A company focused on building and optimizing AI-powered platforms, delivering scalable, high-impact AI solutions to solve real-world problems.

What you will do

• Design, build, and deploy AI-powered features within production-grade applications.
• Develop backend services and APIs that integrate LLMs into real-world products.
• Build and optimize LLM-based workflows, including prompt engineering, RAG systems, and agent frameworks.
• Own end-to-end delivery of AI features, from ideation to deployment and monitoring.
• Collaborate with cross-functional teams to integrate AI capabilities into scalable systems.
• Evaluate and improve LLM performance using testing frameworks and metrics.

Requirements

• Located in Colombia (only).
• English: B2+ or C1 level required.
• 4-5 years of experience as a Software Engineer or AI Engineer in product-focused roles.
• Proficiency in Python and experience building backend systems, APIs, and integrations.
• Hands-on experience integrating LLMs (GPT-4, Claude, Gemini, Llama) and building RAG systems.
• Strong software engineering fundamentals in data structures, system design, and clean code.

Nice to have

• Experience deploying AI services on cloud platforms (AWS, GCP, Azure).
• Experience with modern backend or full-stack frameworks.
• Familiarity with big data tools such as Hadoop or Spark.
• Contributions to open-source AI projects.