Senior AWS Agent Platform Engineer (DevOps / Backend – AI Agent Systems)

Senior AWS Agent Platform Engineer (DevOps / Backend – AI Agent Systems)

Location: Remote from Spain (an indefinite Spanish employment contract)

Project Overview

We are building a next-generation AI agent platform on AWS , enabling scalable, observable, and secure agent execution across enterprise use cases. The platform leverages agentic frameworks, event-driven architectures, and cloud-native DevOps practices to support intelligent workflows and automation.

You will contribute to the core platform capabilities such as orchestration, registry, observability, and policy enforcement—helping to shape a highly scalable and production-grade AI ecosystem.

What You Will Do

• Design and develop cloud-native backend services for AI agent orchestration on AWS
• Build and maintain event-driven, distributed systems using modern DevOps practices
• Implement CI/CD pipelines, infrastructure automation, and deployment strategies
• Develop and integrate APIs, microservices, and backend components for agent lifecycle management
• Ensure scalability, reliability, and performance of platform services
• Collaborate with cross-functional teams (ML, platform, DevOps, frontend)
• Implement monitoring, logging, and alerting mechanisms
• Contribute to architecture decisions and system design
• Troubleshoot production issues and ensure system stability

Must-Have Requirements

• 5+ years of experience in backend engineering / DevOps / platform engineering
• Strong experience with AWS (Lambda, ECS/EKS, S3, IAM, CloudWatch, etc.)
• Solid knowledge of microservices and distributed systems architecture
• Experience building and consuming RESTful APIs
• Hands-on experience with CI/CD pipelines (Jenkins, GitHub Actions, etc.)
• Proficiency in containerization (Docker) and orchestration (Kubernetes is a plus)
• Strong coding skills (Python, Node.js, or similar)
• Experience with event-driven systems (e.g., Kafka, SQS, SNS)
• Understanding of observability, logging, and monitoring best practices
• Familiarity with security and access control (IAM, policies)
• Experience working in Agile environments

Nice-to-Have – Focus Area Differentiation

1. Agentic Framework (LangGraph Focus)

• Experience with LangGraph, LangChain, or similar agent frameworks
• Understanding of LLMs and agent orchestration patterns
• Experience building multi-step AI workflows and tool integrations
• Knowledge of prompt engineering and agent reasoning pipelines

2. Registry Focus

• Experience designing service/agent registries or metadata management systems
• Familiarity with service discovery, schema/version management
• Experience with API gateways and service catalogs
• Knowledge of artifact/version lifecycle management

3. Policy Focus

xkdbapo
• Experience implementing policy enforcement systems (RBAC, ABAC, OPA, etc.)
• Strong understanding of security, compliance, and governance frameworks
• Familiarity with policy-as-code and access control patterns
• Experience working with sensitive data and secure system design

4. Observability Focus

• Experience building observability platforms (logs, metrics, traces)
• Hands-on with tools like Prometheus, Grafana, ELK, OpenTelemetry
• Knowledge of distributed tracing and performance monitoring
• Ability to design alerting and incident response systems

What We Offer

• Opportunity to work on cutting-edge AI agent platforms
• Modern cloud-native architecture on AWS
• High-impact role in a scalable, enterprise-grade system
• Collaborative, innovation-driven environment

La siguiente información ofrece un resumen de las habilidades, cualidades y cualificaciones necesarias para este puesto.

Hay opciones de teletrabajo/trabajo desde casa disponibles para este puesto.