CorpTen

Compensation

Full Description

Overview Cumulus IT Solutions, a growing IT consulting and professional services company, is seeking experienced and highly skilled AI Engineers / Copilot Studio Engineers to support a large enterprise customer in advancing their Generative AI and Enterprise AI platform initiatives. This is a fully remote contract opportunity with an initial engagement of 6 to 12 months, with the potential for extension based on project needs and performance. We are seeking hands-on engineers with expertise in Microsoft Copilot & Copilot Studio, Anthropic Claude, and Google Gemini technologies. Candidates may specialize in one platform or possess experience across multiple AI ecosystems. The ideal candidate will have a combination of platform engineering, AI solution development, security and governance expertise, and enterprise integration experience. These professionals will play a critical role in designing, implementing, securing, and operationalizing enterprise AI solutions while enabling business users to safely leverage advanced AI capabilities on a scale. Engagement Details • Position Type: Contract (1099 or Corp-to-Corp) • Location: 100% Remote • Contract Duration: 6–12 Months Initial Term • Extension: Possible based on project requirements and performance • Compensation: Negotiable based on experience and expertise • Work Authorization: Candidates must be authorized to work in the United States • Corp-to-Corp (C2C): Supported We are looking for strong technical contributors who can work independently, collaborate with customer stakeholders, and deliver enterprise-grade AI solutions in fast-paced environments. Candidates with cross-platform expertise spanning Copilot Studio, Claude, and Google Gemini are highly desirable. Platform Engineering & Administration • Serve as a technical subject matter expert for Microsoft Copilot Studio, Anthropic Claude, and/or Google Gemini platforms. • Configure, administer, and optimize AI platform settings, governance controls, security controls, and environment configurations. • Maintain platform operational health and ensure compliance with enterprise standards. Agent Development & Orchestration • Design, build, test, and deploy sophisticated AI agents and copilots. • Develop multi-agent orchestration solutions to support complex enterprise business processes. • Build reusable skills, prompts, plugins, and AI-powered workflows across multiple business domains. • Integrate enterprise systems, APIs, and data sources into AI solutions. MCP and Connector Development • Design and implement custom Model Context Protocol (MCP) servers and integrations. • Develop and maintain enterprise-grade connectors and reusable AI skills. • Support data connector onboarding and lifecycle management from intake through production deployment. • Integrate identity providers, permission models, and enterprise access controls. Security, Risk & Governance • Conduct security assessments of third-party connectors, plugins, skills, and MCP implementations. • Evaluate risks related to prompt injection, data leakage, unauthorized access, and data exfiltration. • Perform architecture reviews and create mitigation strategies for identified risks. • Ensure AI platform implementations meet enterprise security, privacy, and compliance requirements. Platform Enablement & Operations • Manage connector registration, platform onboarding, and capability distribution. • Configure skill and plugin distribution based on enterprise-wide or group-level access requirements. • Develop documentation, implementation guides, and operational procedures. • Provide technical guidance and support for internal stakeholders adopting AI capabilities. Automation & DevOps • Implement Infrastructure as Code (IaC) solutions using Terraform and related tooling. • Build CI/CD pipelines for AI platform provisioning, deployment, testing, and governance. • Automate platform configuration, registration, and release processes across Development, Test, and Production environments. • Establish monitoring, logging, and operational health dashboards for AI services. Required Qualifications Technical Experience • 5+ years of software engineering, platform engineering, cloud engineering, or AI engineering experience. • 1+ years of hands-on experience with Microsoft Copilot Studio, Anthropic Claude, Google Gemini, or comparable Generative AI platforms. • Demonstrated experience building enterprise-grade AI agents and copilots. • Strong understanding of Large Language Models (LLMs), Retrieval Augmented Generation (RAG), prompt engineering, and agent architectures. • Experience implementing Model Context Protocol (MCP) integrations and custom AI tooling. Cloud & Integration Skills • Experience integrating enterprise applications using REST APIs, Graph APIs, webhooks, and connector frameworks. • Experience working with Azure, Google Cloud Platform, or other enterprise cloud services. • Knowledge of identity and access management concepts including OAuth, SAML, OpenID Connect, and Entra ID. Security & Governance • Experience reviewing AI applications and integrations for security, compliance, and operational risks. • Understanding of: • * Prompt Injection Risks • Data Leakage Prevention • AI Governance Frameworks • Secure Plugin and Connector Development • Enterprise Access Controls DevOps & Automation • Experience building CI/CD pipelines using Azure DevOps, GitHub Actions, GitLab, or similar tools. • Proficiency with Terraform and Infrastructure as Code methodologies. • Experience supporting automated deployments across multiple environments. Preferred Qualifications • Microsoft Copilot Studio certification(s). • Azure AI Engineer Associate certification. • Google Cloud Generative AI certification. • Experience with: • * Azure OpenAI • Semantic Kernel • ChatGPT • LangChain • AutoGen • CrewAI • Vector Databases • Knowledge Graphs • Enterprise Search Platforms • Microsoft M365 Admin Center • Experience implementing multi-agent orchestration frameworks. • Familiarity with enterprise governance and responsible AI frameworks. Key Competencies • Deep technical troubleshooting capability • Strong stakeholder engagement and communication skills • Security-first mindset • Ability to work independently with minimal supervision • Experience operating in large enterprise environments • Ability to balance innovation with governance and risk management