IT Infrastructure Engineer

About REVEL

REVEL is an AI robotics company developing physical intelligence for general-purpose humanoid robots. We capture the force, dexterity and intent of human work with our Neural Gambit wearable, and use it to train RAI, the intelligence that powers our robots. Our R&D and engineering facilities are in Prague, Czech Republic. This role is on-site with our team in Prague.

The company was founded in 2025 and is building its founding team in the Czech Republic. Capture sessions, model training, the print fleet, and robot test rigs all depend on local network, storage, and compute.

The role

You will design and operate the physical and computational infrastructure that the engineering, machine learning, and content teams depend on: the network, the servers, the storage, and the compute those teams train and test on. You own everything from the cable in the wall to the job scheduler on the GPU nodes.

The work is hands-on and varied: racking and configuring hardware, designing network segmentation, diagnosing faults from firmware through to the kernel, and writing the provisioning and monitoring tooling that keeps it all visible. The systems are currently small enough for one person to administer directly, and are expected to grow quickly as capture volume and training load increase.

This role is paired with an IT Administrator who owns enterprise systems, identity and end-user support. You own the infrastructure layer; they own the accounts, devices and applications that sit on top of it. You will work closely together, and neither of you will be waiting on the other for the parts you own.

Responsibilities

• Design, build and operate the network: switching, routing, VLAN segmentation, firewalls, site-to-site and remote-access VPN, and wireless coverage across office, lab and workshop.

• Run the network services the sites depend on: DHCP, internal DNS, NTP, RADIUS and certificate-based network authentication, and the ISP and failover links behind them.

• Manage the physical estate: servers, GPU nodes, NAS and backup storage, racks, structured cabling, PDUs, UPS units, and the compute and peripherals attached to capture and test rigs. Maintain an inventory, a firmware baseline and a replacement schedule.

• Build the computational infrastructure on top of that: shared high-throughput storage for capture and training data, job scheduling and GPU allocation, environment provisioning, and container and image registries, so that available CPU, GPU and disk capacity is used efficiently and fairly.

• Own backup and recovery for research data and infrastructure state, including offsite copies, restore testing and a documented recovery plan for the training and capture pipelines.

• Write internal tooling: monitoring, alerting, inventory, capacity and usage reporting, and simple web interfaces for administration.

• Diagnose hardware and network faults, from cabling and optics through to driver, firmware and kernel-level problems, including GPU, NVMe and high-throughput networking issues.

• Work with vendors, integrators and support organisations on warranties, RMAs, escalations and infrastructure procurement.

• Support other teams with their infrastructure: advise on what they build themselves, resolve the issues they report, and write documentation so common problems can be handled without you.

Requirements

• 3+ years of relevant professional experience

• Practical understanding of modern network infrastructure: L2/L3 switching, routing, VLANs, DHCP/DNS, firewalls, VPN and enterprise wireless.

• Linux administration and bash. You can install, configure, automate and troubleshoot Linux systems from the command line, including storage, networking and boot-level problems.

• Programming skills sufficient for internal tooling: scripts, small services and simple web interfaces for administration and monitoring. Python or an equivalent language.

• Comfort working with physical hardware: racking, cabling, replacing components, and reading a vendor manual to the end.

• Communication skills, and willingness to work on other people’s problems, including explaining causes and fixes to non-specialists.

Nice to have

• Compute cluster administration (Slurm, Kubernetes or equivalent), including GPU scheduling and shared high-throughput storage.

• Storage engineering: ZFS, Ceph, NFS or SMB at scale, tiering, and multi-terabyte dataset handling.

• Configuration management and infrastructure-as-code (Ansible, Terraform, NixOS or similar).

• Monitoring stacks such as Prometheus and Grafana.

• Experience supporting a lab, workshop or manufacturing environment, including OT or machine networks kept separate from the office network.

• Hybrid or cloud experience (AWS, GCP or Azure) for burst training capacity and offsite backup.

What you'll get out of it

• Full ownership of the infrastructure layer, including architectural decisions.

• Hardware and model development in the same building, so the results of infrastructure work are visible directly.

Why REVEL

• Work That Ships: We capture how skilled humans work, their force, touch, and judgment, and our robots do the work. You put robots on a paying customer's floor, not in a demo loop

• The Team: Colleagues from NVIDIA, SpaceX, and Neura Robotics, and founders you work with directly. No layers, no process between you and the decisions

• Your Own Hardware: A top-spec GPU workstation, cluster access, and hands-on time with the robots you're building. Not a software sandbox

• Keep Learning: Conference budget for select roles (GTC, CoRL, ICRA), and room to publish and contribute to open source where our IP allows

What we offer

• Unlimited Paid Time Off: Real flexibility to take time away when you need it. We trust our people to own their work, their time, and their results

• Prague, On-Site: Robots need hands, so we work together in our Prague lab. Moving here? We sponsor your work visa and cover relocation

• Lunch, On Us: Complimentary lunch every working day, plus coffee, snacks, and drinks whenever you need a boost

How to apply

• Apply through the link on this posting.