Sr. Cloud Engineer

I am not interested in working with any third party agencies; your mails will be deleted nor can we work with anyone that requires sponsorship now or in the future in the US.

This is a contract to hire role.

Role overview

Our client is hiring an Infrastructure Engineer to lead the next generation of IT infrastructure — one that runs on automation, integrates AI-powered tooling, and connects systems through modern APIs and Model Context Protocol (MCP). The right candidate goes beyond keeping the lights on. They identify repetitive operational processes, design intelligent automation to eliminate them, and actively evaluate how emerging AI capabilities can be embedded into IT workflows.

This role sits at the intersection of traditional infrastructure ownership and AI-enabled operations. You will own the reliability and security of our hybrid cloud environment while driving measurable reductions in manual IT workload through automation and intelligent system integration. Need a blend of Cloud, infrastructure, security, DevOps and AI integration.

Key responsibilities

Cloud infrastructure and system administration

• Administer macOS, Windows 10/11, and Windows Server environments with a focus on reducing manual administration through intelligent tooling.

• Manage Azure AD / Entra ID, Conditional Access policies, and Azure AD Domain Services, including Group Policy, authentication, and access control.

• Administer Microsoft 365 (Exchange Online, SharePoint, OneDrive, Teams) and endpoint management platforms (Intune).

• Support Azure cloud infrastructure, hybrid connectivity, and platform-as-a-service workloads.

Networking and security

• Support and troubleshoot hybrid networking infrastructure, including VPNs, firewalls, DNS, DHCP, and VLANs.

• Collaborate with the security team to maintain HIPAA, HITRUST, and NIST compliance across all managed systems.

• Implement and monitor EDR/XDR solutions and integrate security telemetry into automated alerting and response workflows.

Monitoring and reliability

• Build and maintain automated monitoring pipelines that surface anomalies before they escalate, reducing mean time to detection.

• Develop self-healing runbooks and AI-assisted incident response workflows to reduce escalation volume and on-call burden.

• Document all automation, integrations, and infrastructure changes in a centralized, version-controlled knowledge base.

AI integration and intelligent automation

• Design and deploy AI-powered automation workflows that replace repetitive IT processes — including ticket triage, access provisioning, patch scheduling, and system health alerting.

• Implement and manage MCP-based integrations that allow AI agents and internal tools to interact with IT infrastructure components, identity systems, and cloud services.

• Evaluate, pilot, and operationalize large language model (LLM)-driven tools for IT operations — including AI-assisted scripting, anomaly detection, and runbook generation.

• Partner with engineering and product teams to ensure AI infrastructure integrations meet security, compliance, and audit requirements.

API and systems integration

• Build and maintain REST and GraphQL API integrations that connect Microsoft 365, Azure, endpoint management tools, and third-party IT platforms.

• Design integration architectures using MCP servers to expose IT system capabilities to AI agents and internal automation pipelines.

• Develop and maintain automation libraries in Python and PowerShell, moving beyond one-off scripts toward reusable, version-controlled infrastructure-as-code.

• Manage identity and access workflows through API-driven automation across Azure AD / Entra ID, and Intune.

Collaboration and IT support

• Provide Tier 3 support for escalated infrastructure issues, applying automation tooling to accelerate resolution.

• Work directly with DevOps, security, and software engineering teams to align IT infrastructure investments with product and platform roadmaps.

• Participate in disaster recovery planning and business continuity design, with an emphasis on automating failover and recovery procedures.

Qualifications and experience

Required:

• Five or more years of experience in systems engineering or systems administration demonstrated ownership of complex hybrid cloud environments.

• Hands-on experience implementing AI tools or LLM-powered workflows in an IT operations context — including prompt engineering, API integration, or agent orchestration.

• Working knowledge of Model Context Protocol (MCP): how MCP servers are structured, how AI agents consume tool definitions, and how to expose IT system capabilities through MCP endpoints.

• Strong API fluency: experience building and maintaining REST API integrations using Python, PowerShell, or equivalent, with version control and documentation practices.

• Proficiency in Microsoft 365, Azure AD / Entra ID, and Azure cloud services.

• Experience with endpoint management platforms (Intune).

• Networking fundamentals: TCP/IP, DNS, DHCP, VPN, VLANs, and firewall management.

• Demonstrated experience in a healthcare IT or regulated environment (HIPAA, HITRUST, NIST).

Preferred:

• Experience building AI agent workflows using frameworks such as LangChain, AutoGen, or custom MCP server implementations.

• Familiarity with infrastructure-as-code and GitOps practices (Terraform, Bicep, or equivalent).

• Background in DevOps or platform engineering, with exposure to CI/CD pipelines and containerized workloads.

• Microsoft Certified: Azure Administrator Associate, MCSE, or equivalent certification.