hirly

Panthalassa

Senior HPC Platform Engineer

Portland, OR

hirly Pro

Get in front of the people hiring at Panthalassa

  • Reach the hiring manager at Panthalassa on LinkedIn, from your own account
  • hirly applies to this job for you, with unlimited applications
  • A resume and cover letter written for this job, unlimited
  • The hiring manager and recruiter at Panthalassa, with contact details
Get Pro for this job →

$49 a month · ₹1,999 for 30 days in India · cancel any time

See how you match this job — and similar ones. Free.

Upload your resume and hirly scores it against this role at Panthalassa first, then against similar open jobs, and shows where you fit and why.

PDF or DOCX, up to 12MB. No sign-up to see your matches.

Get past the screening software and onto a recruiter's desk

hirly rewrites your resume for this job — matching the keywords and skills in the posting, moving your most relevant experience to the top, and writing a cover letter to fit. About 30 seconds.

  • Keywords matched to this posting
  • Fit score before you apply
  • Cover letter included

Matched against 2.3M live jobs from 220,000+ employers in 200+ countries.

Tailor my resume for this job →

Apply from your AI assistant

Connect hirly to Claude or ChatGPT and ask it to apply to this job. hirly tailors your resume, fills the employer’s form and asks before sending.

Some employer sites stop an application at a CAPTCHA or sign-in and hand it back with a link. Applying needs a paid plan. Works with any assistant that supports MCP.

hirly's read of this role

Role family
Engineering
Seniority
Senior
Country
US
Work mode
Remote-friendly
First seen by hirly
20 Nov 2026

Derived automatically from the posting. Upload your resume above to see how the role scores against it.

the posting

About the Company

We are a renewable energy and ocean technology company committed to rapidly developing and deploying technologies that will ensure a sustainable future for Earth by unlocking the vast energy potential of its oceans. Our focus is on capturing civilizational levels of ultra-low-cost renewable energy for applications including computing and affordable renewable fuels delivered to shore.

The company is a public benefit corporation headquartered in Portland, Oregon, and backed by leading venture capitalists, philanthropic investors, university endowments, and private investment offices. We operate as an idea meritocracy in which the best ideas change the company’s direction on a regular basis.

Our staff have worked at organizations such as SpaceX, Blue Origin, Boeing, Tesla, Apple, Virgin Orbit, Astra, Google, Amazon, Microsoft, New Relic, Bridgewater, Raytheon, Disney Imagineering, and the US Army and Air Force, as well as research universities, startups, and small companies across a range of industries.

About the Job

Our core technology is the node, a device that produces energy in the ocean’s harshest conditions for years at a time without human maintenance or intervention.

You will join Panthalassa's Compute Infrastructure team, a small platform engineering team that builds and operates shared infrastructure as internal products. The team owns a Kubernetes-based compute platform on GKE (ArgoCD, GitHub Actions runners, Terraform modules) and is bringing our on-premises HPC clusters under the same model: a managed HPC platform that CFD engineers consume through a documented golden path rather than through ad-hoc requests to an administrator. Your work will directly support our mission to deliver abundant renewable energy and affordable green fuels.

You will own that HPC platform end to end: Linux, Slurm, storage, interconnects, provisioning, and scientific software. Your initial scope is our primary CFD cluster, with the expectation that you grow into ownership of our second cluster and define how both are operated under the same configuration management and operational standards as the rest of our infrastructure.

This is a hands-on role with broad ownership and room to shape how our computing infrastructure grows. You will work closely with CFD engineers on production workloads and performance, and with an on-site datacenter technician who carries out physical hardware work. We are looking for someone who follows problems through to resolution, communicates clearly, and builds systems that others can operate confidently and that engineers can consume without needing to understand how they work underneath.

The services running on these clusters, including scheduling, software environments, storage, and license servers, are products with users. You will treat them that way: measure how they are used, reduce friction, and iterate.

Candidates should have strong interpersonal skills and be able to thrive in a creative, scrappy, and collaborative environment in which the best ideas change the company’s direction on a regular basis.

Responsibilities

Platform

Contribute to defining the HPC platform as a product: its service catalog, service levels, and roadmap, in partnership with CFD engineering leads, and prioritize work by user impact.

Build the golden path for running simulations: standard job templates, submission tooling, software environment conventions, and documentation that lets a new CFD engineer go from zero to a correctly placed production job without a ticket.

Replace manual, ticket-driven operations with self-service wherever practical: account and project onboarding, storage allocation, module requests, license visibility, and job diagnostics.

Instrument platform usage and health (utilization, queue wait, job failure modes, storage growth) and use it to drive capacity planning and roadmap decisions.

Contribute to shared team tooling and conventions so HPC and cloud compute are operated the same way.

Design future HPC capacity and workflows with the GKE platform in mind: burst, hybrid scheduling, shared identity, and shared artifact and container registries.

Platform operations

Automate cluster configuration with Ansible and Git so system state is reproducible, reviewable, and applied through CI. Manual changes to cluster state are the exception, not the norm.

Own the day-to-day operation, configuration, and reliability of our HPC clusters, including compute and head nodes, storage, and interconnects.

Plan and bring up new compute capacity: specify hardware, define rack and network layouts, and provision and validate nodes after installation.

Administer Slurm end to end, including partitions, QoS, accounting, scheduling policy, and job troubleshooting for CFD engineers.

Build and maintain scientific software environments, including Environment Modules or Lmod, MPI stacks, and compiler toolchains tuned for our interconnects.

Manage diskless provisioning with Warewulf, including PXE and UEFI boot, node images, kernel and driver pinning, and firmware lifecycle.

Operate Omni-Path and InfiniBand fabrics, including subnet management, link health, topology validation, and MPI performance verification.

Manage BMC and IPMI access, firmware updates, and remote diagnosis of memory, NIC, and storage faults. Coordinate hardware suppliers and RMAs.

Work with our on-site datacenter technician on hardware installations, drive and DIMM swaps, cabling, and network changes, providing clear diagnoses and precise instructions.

Administer shared simulation storage, including ZFS pools, NFS exports, scrub and snapshot schedules, capacity planning, and backup coverage.

Build monitoring and alerting for nodes, fabric, scheduling, and storage, with runbooks that allow others to respond effectively, and expose user-facing status and job dashboards so engineers can self-diagnose. Maintain operational procedures in Confluence, including emergency runbooks and instructions for on-site work.

Partner with CFD engineers on profiling, process placement, and tuning of production HELYX / OpenFOAM-family and Star-CCM+ jobs, and turn findings into reusable defaults such as process placement, MPI settings, and job templates, rather than one-off fixes.

Required Qualifications

5+ years of experience operating production Linux HPC clusters, or equivalent experience building compute platforms for scientific or batch workloads, with deep hands-on knowledge of Slurm configuration, accounting, and scheduling policy.

Experience taking over an inherited cluster, auditing and documenting its configuration, and bringing it under your own configuration management.

Experience with diskless or stateless provisioning using Warewulf, xCAT, or similar tools, including PXE and UEFI boot troubleshooting.

Experience operating Omni-Path or InfiniBand interconnects and validating MPI performance.

Proficiency with BMC, IPMI, or Redfish management and remote hardware fault diagnosis on bare-metal servers.

Experience building scientific software stacks with Environment Modules or Lmod, MPI libraries, and compilers, and managing configuration with Ansible and Git.

Experience operating infrastructure as an internal product: defining service levels, building self-service tooling or interfaces, and prioritizing work by user impact rather than ticket order.

Experience with infrastructure-as-code and GitOps workflows beyond cluster configuration management, including Terraform, CI pipelines, and pull-request-driven change.

Familiarity with CFD or other engineering simulation workloads, including scaling behavior and scheduler, storage, and fabric requirements.

Experience implementing infrastructure monitoring and alerting, building user-facing dashboards, and writing runbooks others can follow.

Ability to guide on-site staff through physical hardware work remotely with precise, unambiguous instr

Original posting on Panthalassa's site ↗

Listed on hirly, a job board. hirly is not the employer: Panthalassa is hiring for this role.

Browse similar roles

Want this one?

Upload your resume and hirly rewrites it for this job and writes the cover letter — in about thirty seconds, before you sign up.

Tailor my resume for this job