AI Platform Engineer: End-to-End LLM & Ops (Remote)

Caseware; Colombia; Presencial; COP 168.000.000 - 300.000.000; Jornada completa

Descripción de la vacante

Caseware Colombia seeks a senior engineer to own and operate an AI platform in production, including architecture, delivery, and on-call responsibilities. You will design and run LLM services, memory systems, and agent orchestration, ensuring reliability and cost-efficient performance.

You will mentor developers, lead SDLC improvements, and evaluate avai­lable AI tools, while collaborating with Tech Leads, Security, and Product teams in a fast-paced, evolving environment.

Formación

• 2+ years building and operating production AI systems.
• Experience with agent frameworks, memory systems, or orchestration of tool-using AI systems.
• Proficiency with production AWS including Infrastructure as Code.
• Degree in Computer Science, Software Engineering, or equivalent; 8+ years of software development experience.
• Proven experience designing and operating distributed, cloud-native SaaS platforms at scale, preferably on AWS.

Responsabilidades

• Create architecture, prototypes, and design proposals delivering near-term business value.
• Influence technical direction through architecture reviews and RFCs.
• Partner with senior developers to define and execute the product/platform architecture roadmap.
• Balance speed, quality, and maintainability for long-term platform health.
• Break down large initiatives into parallelizable work delivering incremental value.
• Champion proposals through the SDLC from design to production.

Conocimientos

AI systems production

Agent frameworks

AWS / Cloud

Distributed systems

REST/GraphQL APIs

Mentoring

Educación

BS in CS or Software Engineering

Herramientas

AWS

CDK / CloudFormation / Terraform

CI/CD pipelines

GitHub Actions

Descripción del empleo

Caseware Colombia seeks a senior engineer to own and operate an AI platform in production, including architecture, delivery, and on-call responsibilities. You will design and run LLM services, memory systems, and agent orchestration, ensuring reliability and cost-efficient performance.

You will mentor developers, lead SDLC improvements, and evaluate avai­lable AI tools, while collaborating with Tech Leads, Security, and Product teams in a fast-paced, evolving environment.