Remote AI Production Engineer: Backend & RAG Systems

Cadre AI; United States; À distance; USD 39 000 - 50 000; Plein temps

Résumé du poste

Cadre AI is hiring an AI Engineer to serve as the technical backbone of its delivery engine, building production-grade AI systems and agentic workflows. You will co-develop requirements with strategists, ship scalable components, and abstract common patterns into internal tools for faster future deliveries.

You will own end-to-end delivery of AI components, from scaffold to deployment, and ensure systems run reliably in client environments while keeping latency and costs in check.

Qualifications

• 3+ years of backend engineering experience, incl. AI agents in prod.
• Hands-on with vector databases, RAG optimization, and agentic orchestration.
• Proficiency in Python and Node.js, API design, async processing, and secure creds.
• IaC tooling experience (Terraform/Pulumi); Docker/Kubernetes in production.
• Ability to build generic, reusable components across clients.

Responsabilités

• Design and build complex backend AI modules: agentic workflows and multi-step reasoning.
• Translate blueprints into production-ready code with error handling and observability.
• Own end-to-end delivery of AI components from scaffold to deployment.
• Use AI coding assistants to accelerate output while maintaining quality.
• Architect and optimize RAG pipelines over unstructured data sources.

Connaissances

Backend engineering

Production AI systems

Python

Node.js

Systems design

Ownership

Outils

Terraform

Pulumi

Docker

Kubernetes

Vector databases

Description du poste

Cadre AI is hiring an AI Engineer to serve as the technical backbone of its delivery engine, building production-grade AI systems and agentic workflows. You will co-develop requirements with strategists, ship scalable components, and abstract common patterns into internal tools for faster future deliveries.

You will own end-to-end delivery of AI components, from scaffold to deployment, and ensure systems run reliably in client environments while keeping latency and costs in check.