Digital Engineer; HPC Engineer

This position is open for external candidates only to apply.

The High Performance Computing (HPC) Division at Los Alamos National Laboratory provides scientific computing resources consisting of some of the largest HPC systems in the world, as well as numerous large commodity cluster systems. Our Support Services Team within the HPC Systems Group (HPC-SYS) provides resources for both our internal HPC admin teams and our external users by building and maintaining RHEL systems, managing our admin- and user-facing Open Shift cluster, and supporting around 1,000 users with services such as Git Lab.

We are expanding this team's charter to include the modernization of our backend infrastructure to support AI-driven and agentic workflows. The Support Services Team is seeking a Digital Engineer who can operate across two closely related domains: traditional Linux/container systems administration, and the design of secure, agent-ready data access architecture across our databases and data stores.

This is a hybrid role - roughly half of the position will continue our current systems administration mission (RHEL, Open Shift, Git Lab, Ansible), and half will be dedicated to redesigning and hardening our backend so that databases, storage systems, and internal tools can be safely and reliably accessed by AI agents and automated tooling.

• Deploy, maintain, and improve RHEL and container-based systems supporting the HPC Division
• Administer and grow our Open Shift cluster, including build, test, and troubleshooting of new hardware and workflows
• Support Git Lab and other internal services for approximately 1,000 users
• Participate in periodic on‑call rotation for RHEL servers and Open Shift systems
• Develop and maintain configuration management via Ansible
• Mentor students, junior staff, and peers; produce technical documentation, presentations, and reports

• Assess and redesign backend infrastructure - databases, object storage, and other data stores - to support secure, structured access by AI agents and automated systems
• Design and implement role-based access control (RBAC) across multiple heterogeneous databases and storage systems, exposed via APIs or Model Context Protocol (MCP) interfaces
• Build, deploy, and manage MCP servers that expose internal data and tools to agentic AI systems in a controlled, auditable manner
• Establish patterns and guardrails for how agentic tools discover, query, and act upon internal data, ensuring least‑privilege access and traceability
• Evaluate and integrate API gateways, service meshes, or proxy layers as needed to mediate agent‑to‑datastore communication
• Collaborate with data owners, security, and application teams to define access policies, authentication/authorization models, and data governance appropriate for AI/agent consumption
• Stay current on the evolving agentic AI tooling landscape (e.g., MCP, function‑calling frameworks, agent orchestration platforms) and translate that knowledge into practical backend design decisions

This position will be filled at the HPC Engineer 2 level.

• Demonstrated experience building, configuring, and administering production Linux systems, including strong command‑line skills and working knowledge of hardware/software security practices
• Strong scripting/automation skills in Bash, Python, Perl, or similar
• Experience with a centralized configuration management system such as Ansible
• Experience using Git for version control
• Strong understanding of containers and one or more orchestration systems such as Kubernetes or Open Shift
• Practical experience with relational and/or non‑relational databases (e.g.,…