AI Platform Integration Engineer

Are you an experienced cloud or AI platform engineer looking for a part-time opportunity to work with emerging AI technologies? Do you have hands-on experience with AWS AI services, Model Context Protocol (MCP), and API integrations?

Opportunity

Virtual Service Operations (VSO) is seeking an experienced AI Platform Integration Engineer to support a high-visibility enterprise technology modernization initiative on a part-time basis, approximately 20 hours per week.

This initiative focuses on developing foundational platforms and services that enable secure data connectivity, interoperability, and AI integration across a large, complex enterprise environment. The project involves establishing reusable capabilities that allow enterprise applications, data services, and AI-enabled tools to interact through standardized APIs and Model Context Protocol (MCP) servers.

In this role, you will support the integration of AI services and MCP capabilities into a shared enterprise platform, enabling AI applications and agents to discover and securely access approved tools and data services.

You will work closely with a dedicated AI Gateway engineering team responsible for developing and maintaining the core gateway infrastructure. Your focus will be on integration, configuration, operational support, and coordination rather than building the gateway itself.

This position includes MCP server hosting, AI usage and cost metering, rate limiting, content-control integration, and technical coordination across engineering teams.

Key Responsibilities

AI Gateway & Platform Integration

• Support integration of enterprise platform services with an existing AI Gateway.
• Collaborate with AI Gateway engineering teams to establish and maintain secure integration interfaces.
• Configure and support AI service connectivity, including model routing and API-based integrations.
• Troubleshoot technical issues involving AI gateway connectivity, service access, and platform integrations.
• Coordinate technical requirements, integration schedules, dependencies, and issue resolution across engineering teams.

Model Context Protocol (MCP) Integration

• Deploy, host, configure, and operate Model Context Protocol (MCP) servers within the enterprise platform.
• Support standardized interfaces that allow AI applications and agents to discover and access approved tools and services.
• Integrate MCP servers with existing APIs and enterprise data services.
• Monitor MCP server availability, connectivity, and operational performance.
• Support secure access to tools and services exposed through MCP interfaces.

AI Usage Monitoring & Cost Management

• Integrate usage tracking and cost metering for AI and Large Language Model (LLM) traffic.
• Support monitoring of token consumption, API usage, and associated AI service costs.
• Configure or integrate reporting capabilities that support consumption visibility and internal cost allocation.
• Collaborate with platform teams to establish appropriate usage limits and monitoring practices.

API Security, Rate Limiting & Content Controls

• Configure and support rate limiting, quotas, and usage restrictions for AI endpoints.
• Integrate content-control and AI guardrail services into gateway request and response workflows.
• Support implementation of security and usage policies for AI-enabled applications.
• Assist with the integration of AWS AI services, including Amazon Bedrock and related capabilities.
• Troubleshoot API connectivity, authorization, and configuration issues.

Technical Collaboration & Documentation

• Serve as a technical liaison between the enterprise platform engineering team and the AI Gateway engineering team.
• Coordinate integration requirements, technical interfaces, schedules, and issue resolution.
• Provide clear technical updates to engineering teams and project stakeholders.
• Document AI service integrations, MCP server configurations, operational procedures, and troubleshooting processes.
• Support initial Minimum Viable Product (MVP) delivery and identify opportunities for future platform enhancements.

Required Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Information Technology, or a related technical discipline, or equivalent professional experience.
• Minimum of 3 years of hands-on professional experience in software engineering, cloud engineering, or platform engineering.
• Working knowledge of AI/LLM gateway concepts, including model routing, token-based usage tracking, rate limiting, and content guardrails.
• Hands-on experience deploying or hosting MCP servers, or comparable integrations that expose tools and APIs to AI applications or agents.
• Hands-on experience with AWS cloud services, including Amazon Bedrock or Amazon SageMaker.
• Experience working with API gateways and REST APIs.
• Understanding of cloud-based application integration, service connectivity, and API security.
• Strong troubleshooting and technical problem-solving skills.
• Excellent written and verbal communication skills, with the ability to coordinate effectively across multiple technical teams.
• Ability to work independently and manage technical deliverables in a part-time capacity.

Preferred Qualifications

• Experience developing, extending, or customizing Model Context Protocol (MCP) servers.
• Experience with LLM gateway or proxy technologies such as LiteLLM, Kong AI Gateway, or comparable platforms.
• Experience implementing AI usage metering, token consumption tracking, chargeback reporting, or FinOps capabilities.
• Experience with Amazon Bedrock Guardrails or comparable AI content-control services.
• Experience configuring AI gateway rate limiting, quotas, and usage policies.
• Familiarity with AI agent architectures and tool integration patterns.
• Experience integrating AI services with enterprise applications and data platforms.
• Experience supporting cloud-native platforms in large enterprise or regulated environments.
• Familiarity with security, access management, and governance considerations for enterprise AI integrations.

• This is a fully remote part-time position. Candidates must be able to work independently, communicate effectively, and collaborate successfully with team members in a virtual work environment.
• Bachelor’s degree
• Minimum of 3 years of hands-on professional experience in software engineering, cloud engineering, or platform engineering.
• New hires assigned on this project will be required to undergo and pass drug tests per our client's contract requirements
• Please note that this specific position requires U.S. citizenship status