AI Platform Engineer - 20634

Our client builds and deploys AI agents that perform real operational work for small and mid-sized businesses. These AI agents operate inside customer environments, answering messages, running reports, integrating with business systems, and automating complex workflows.

Each customer receives a dedicated AI agent running on a secure AWS infrastructure. As the company continues to scale, they are seeking an experienced AI Platform Engineer to build, deploy, and operate production-ready AI agents while continuously improving the underlying platform.

The AI Platform Engineer will own the full lifecycle of customer AI agents—from deployment and system integrations to ongoing optimization, monitoring, and platform improvements.

This is a highly technical builder/operator role requiring someone who enjoys solving ambiguous problems, working directly with AI systems in production, and turning customer requests into reliable, scalable solutions. The successful candidate will build integrations, deploy infrastructure, improve observability, optimize AI performance and cost, and ensure every AI agent operates securely and efficiently.

The ideal candidate has strong software engineering fundamentals, production cloud infrastructure experience, and hands-on experience building or supporting AI-powered applications beyond simple chatbot implementations.

• Deploy and manage production AI agents across AWS infrastructure

• Maintain and operate customer-specific AI environments

• Roll out updates safely across live production deployments

• Monitor system performance and ensure platform reliability

• Maintain secure infrastructure using Infrastructure as Code (IaC) principles

• Continuously improve deployment workflows and operational efficiency

• Build and enhance the core AI platform supporting customer agents

• Improve agent orchestration and multi-agent workflows

• Develop platform features that increase scalability, reliability, and performance

• Enhance platform observability, tracing, monitoring, and diagnostics

• Contribute to long-term platform architecture and technical direction

• Build secure API integrations with customer systems, including:

  • CRM platforms

  • Email systems

  • Scheduling platforms

  • Project management tools

  • Business applications

• Develop API wrappers and service connectors for AI agent access

• Handle authentication flows, webhooks, pagination, rate limiting, and data synchronization

• Ensure integrations remain reliable, secure, and maintainable

• Build serverless data pipelines and reporting infrastructure

• Develop ETL workflows using AWS services

• Design data warehouses supporting AI-driven business reporting

• Ensure AI agents have accurate and reliable access to operational business data

• Build reporting tools that provide meaningful business insights

• Design secure credential management processes

• Implement least-privilege access models for AI agents

• Ensure secrets remain securely managed and isolated

• Develop secure authentication and authorization workflows

• Build safeguards that protect customer environments and sensitive information

• Optimize AI agents for speed, reliability, and operational cost

• Improve model selection and inference efficiency

• Reduce unnecessary compute and token usage

• Implement cost monitoring and attribution across customer deployments

• Continuously improve system performance while maintaining high-quality outputs

• Diagnose and resolve production incidents

• Investigate AI agent failures, automation issues, and integration problems

• Build preventative safeguards that reduce recurring operational issues

• Improve system resilience through monitoring and automation

• Maintain high platform availability and customer satisfaction

• • Experience operating LLM-powered agents in production

  • Experience with:

    • Claude Code

    • Agent SDKs

    • LangGraph

    • MCP (Model Context Protocol)

    • Agent orchestration frameworks

  • Experience building or maintaining MCP servers

  • Knowledge of AI observability and evaluation tooling

  • Strong understanding of AI security concepts, including:

    • Prompt injection prevention

    • Least-privilege credential management

    • Secure agent autonomy

  • Experience within startup, consulting, or customer-facing engineering environments

  • Familiarity with AI infrastructure optimization and production monitoring

  ---

Experience with the following technologies is highly preferred:

• TypeScript

• Node.js

• Python

• SQL

• AWS (Lambda, EC2, IAM, S3)

• Terraform

• REST APIs

• Webhooks

• Serverless architecture

• AI agent frameworks

• LLM platforms

• Infrastructure as Code (IaC)

• Git-based development workflows

• CI/CD pipelines

• Fully remote position

• Full-time

• Monday–Friday

• Opportunity to build and operate production AI agents solving real business problems

• Direct ownership of customer-facing AI systems from deployment through optimization

• Exposure to modern AI infrastructure, cloud architecture, and automation technologies

• High-impact engineering role within a fast-moving technical environment

• Opportunity to shape the evolution of an AI platform used daily by customers

• Collaborative engineering culture focused on ownership, rapid iteration, and continuous improvement

• Builder who enjoys shipping production software rather than prototypes

• Strong backend engineer with deep cloud infrastructure experience

• Comfortable operating in ambiguous, fast-paced environments

• Passionate about AI infrastructure and real-world AI applications

• Systems thinker who balances scalability, security, reliability, and cost

• Strong collaborator capable of working directly with customers and internal stakeholders

• Self-starter who takes ownership from idea through production deployment

• Engineer who enjoys solving complex integration and automation challenges

• Reliable deployment and operation of customer AI agents

• Successful delivery of customer-requested AI capabilities

• Platform uptime and operational stability

• Secure and scalable API integrations

• Reduced infrastructure and AI operating costs

• Improved AI agent performance and responsiveness

• Production incident resolution time

• Platform scalability and maintainability

• Customer satisfaction with deployed AI solutions

• Continuous improvement of platform architecture, automation, and observability