Senior Platform Engineer

Company

Cox Automotive - USA

Engineering / Product Development

Sr Software Engineer

Individual ContributorHybrid - Ability to work remotely part of the week

No

Day

Compensation

Compensation includes a base salary in the range of $101,500.00 - $169,100.00. The base salary may vary within the anticipated base pay range based on factors such as the ultimate location of the position and the selected candidate’s knowledge, skills, and abilities. Position may be eligible for additional compensation that may include an incentive program.

Cox Automotive’s Engineering & Technology organization is building a centralized Enterprise AI Integration Platform — the governed infrastructure layer that allows every team in the organization to connect AI agents (Claude, Copilot Studio, Claude Code) to enterprise data sources in a secure, observable, and self-service way. This Senior Platform Engineer will own the technical implementation of that platform: the central AI gateway server, the on-demand connector provisioning engine, the identity-driven session layer, and the observability stack that gives the organization full visibility into every AI tool call made against production data. 

 

This is one of a small number of roles at Cox Automotive working at the intersection of enterprise infrastructure engineering and Model Context Protocol (MCP) — the protocol rapidly becoming the standard interface between AI agents and enterprise systems. The work is novel, the surface area is broad, and the organizational impact is significant. 

 

What You'll Do:

• Design, implement, and optimize the central AI Gateway MCP server — the single governed endpoint through which all AI client connections route, built on FastAPI + uvicorn for high-concurrency enterprise workloads 
• Build and maintain the Redis ElastiCache session layer that binds Microsoft Entra identity to role-resolved MCP tool sets, including token lifecycle management, sliding TTL extension, per-user quota enforcement, and distributed rate limiting 
• Implement the on-demand connector provisioning engine — a system that provisions compute containers with enterprise client drivers, establishes VPC-internal network paths, and retrieves credentials from AWS Secrets Manager automatically when a user’s AI agent declares intent to access a data source 
• Build enterprise system connectors as MCP tool sets: Oracle DB, SharePoint Graph API, Rally, ServiceNow, and a vendor connector approval pipeline with ECR container image scanning and an Aurora-backed connector registry 
• Implement comprehensive automated testing: unit, integration, load testing (1,000+ concurrent users), and chaos testing for connector fault tolerance 
• Build and maintain the full observability stack: structured logging, Prometheus metrics, Kinesis Firehose → OpenSearch indexing, and Grafana dashboards for per-user, per-tool, per-session audit trails 
• Design and implement CI/CD pipelines for all platform components via GitHub Actions, with automated container image builds, ECS task definition updates, and blue/green deployments 
• Own security controls: Entra OIDC token validation, PII masking on all tool responses, WAF rule management, Secrets Manager integration with autorotation, and OWASP-aligned secure API design 
• Maintain and extend the existing Snowflake MCP codebase that forms the foundation of the platform, including session management, RBAC, PII masking, configuration management, and secrets integration modules 
• Develop troubleshooting and diagnostic tools for production support 
• Create documentation, runbooks, and operational playbooks for platform support and maintenance