Senior AI Platform Engineer

Quarterra•Charlotte, NC

3h•Hybrid

About The Position

Reporting to the Senior Director, the Senior AI Platform Engineer builds, deploys, secures, monitors, and maintains Quarterra's enterprise AI and automation environments. This senior individual contributor owns production systems end to end and is accountable for platform reliability, quality, security, and operational performance. The role advances Quarterra's Agentic Workspace and Unified Data Strategy by engineering AI agents, enterprise automations, integrations, and the business context layer that grounds AI outputs. This is an AI engineering and platform ownership role, not a reporting, analytics, or business analysis position. The engineer partners with internal stakeholders, technology team members, and software vendors to move AI capabilities from pilots into reliable production workflows.

Requirements

Bachelor’s degree in Computer Science, Software Engineering, Information Systems, Data Engineering, or a related field preferred; equivalent relevant experience will be considered.
Seven (7) or more years of experience building and operating production software or automation systems, including at least three (3) years of direct accountability for diagnosing and fully resolving production failures.
Professional-level coding proficiency in Python or an equivalent language used regularly to create tested, peer-reviewed, version-controlled, and deployable code.
Demonstrated end-to-end ownership of a live system, including source control, automated build and release, environment promotion, rollback, monitoring, and incident response.
Hands-on integration engineering experience with REST APIs, MCPs, webhooks, authentication, rate limits, retry logic, and direct troubleshooting of integration traffic.
Applied experience with large language models, including retrieval-augmented generation, tool and function calling, orchestration frameworks, prompt and context engineering, and structured outputs.
Experience building or operating systematic evaluation processes for non-deterministic systems, including measuring quality and addressing regression.
Working knowledge of cloud and identity fundamentals, including role-based access management and traceability controls; Microsoft Azure experience strongly preferred.
Experience serving as the internal technical owner of a third-party platform, including upgrade cycles, vendor escalation, and acceptance testing.
Strong written and verbal communication skills, with the ability to train users and explain technical concepts to varied audiences.

Nice To Haves

Extensive experience with Microsoft 365 Copilot, Copilot Studio, Azure AI Foundry, or comparable enterprise agent platforms.
Experience working across Microsoft Azure and Amazon Web Services in multi-cloud environments.
Experience implementing technical controls for a formal audit or compliance program.
Experience in multifamily real estate, development, investment management, financial services, or related deal, operating model, or capital markets workflows.

Responsibilities

Design, build, test, deploy, and maintain AI agents end to end, including retrieval design, context assembly, tool and function definitions, orchestration logic, and structured handoffs when human judgment is required.
Engineer the business context layer that grounds agents, including source connectors, indexing strategy, metadata, permission propagation, data freshness, and reconciliation.
Build evaluation harnesses using test datasets, accuracy and grounding metrics, measured baselines, and regression suites to detect quality drift before and after deployment.
Design guardrails and failure behavior, including confidence thresholds, refusal paths, human review checkpoints, and safe fallback processes when an agent is operating outside reliable boundaries.
Train users on Quarterra AI capabilities and Microsoft Copilot usage, and facilitate recurring learning sessions that support responsible adoption across business functions.
Automate high-volume, rules-based processes such as document intake and extraction, routing, approvals, and data reconciliation using code, APIs, Model Context Protocols (MCPs), and event-driven services.
Build Microsoft 365 automation, including Microsoft Copilot and Copilot Studio extensibility, Microsoft Graph API integrations, SharePoint and Teams solutions, and Power Platform solutions where appropriate, with custom services where required.
Replace manual handoffs with optimized, observable, and idempotent pipelines that can run safely without duplicating work.
Serve as Quarterra’s accountable technical owner for AI and automation platforms, including environments, configuration, releases, upgrades, regression testing, and production support.
Own integrations between Microsoft- and Amazon Web Services-based platforms and Quarterra systems, including APIs, authentication, data contracts, and schema versioning in support of the Agentic Workspace and Unified Data Strategy.
Manage technical support relationships with software vendors, including defect reproduction, escalation, roadmap input, and validation of vendor-delivered work against documented acceptance criteria.
Establish and own service-level key performance indicators for production automations and AI agents, build monitoring that measures performance and accuracy, and lead response and remediation when targets are not met.
Implement least-privilege access for agents and service accounts using enterprise identity tools, ensuring agents follow the permissions of the users they serve and do not access unauthorized data.
Maintain technical controls supporting responsible AI operations, including audit logging, data lineage, prompt and model version control, and change management that produces reliable audit evidence.
Own source control, automated build and release processes, environment promotion, rollback, monitoring, incident response, and root-cause remediation for assigned systems.
Partner with business stakeholders and technology team members to translate operational needs into scalable, secure, and supportable AI and automation solutions.
Communicate technical concepts, risks, system performance, and recommended actions clearly to technical and non-technical audiences.
Continuously evaluate platform performance, emerging capabilities, and workflow opportunities to improve reliability, efficiency, scalability, and user experience.