Inference Server, Powered by NVIDIA Jetson AGX Orin & Jetson Orin NX
Choose a Jetson Orin version
12x Jetson AGX Orin modules or 24x Jetson Orin NX modules
4x 10G SFP+ uplink capability
Supports External NVMe Storage
2U ATX style redundant power supply
See us at DSEI 2025 : S4-260
Inference Server, Powered by NVIDIA Jetson AGX Orin & Jetson Orin NX
GPU-Accelerated Machine Learning and Inferencing Servers Bring Flexibility and Cost Efficiency to High-Powered Computing. Developed in partnership with USES Integrated Solutions, the Inference Server is an extremely low-wattage, high-performance AI workstation powered by the NVIDIA Jetson Orin.
Processing Modules :
12x NVIDIA Jetson AGX Orin or 24x NVIDIA Jetson Orin NX
Out-of-band Management Module :
ARM based OOBM, enabling serial console access, power status monitoring, and power control (ON/OFF)
Processor Module Carriers :
Each module carrier will allow up to 4x AGX Orin OR 8x Orin NX modules to be installed
Internal Embedded Ethernet Switch :
Vitesse/Microsemi SparX-5i VSC7558TSN-V/5CC Managed Ethernet Switch Engine (XDG205)
Internal Array Communication :
12x OR 24x Gigabit Ethernet / 1000BASE-T / IEEE 802.3ab channels
External Uplink Connections :
4x SFP+ 10G uplink
Misc / Additional IO :
1x 1GbE OOB management port via RJ-45; 1x USB UART management port; status LEDs
Input Power :
100~240 VAC (dual redundant) with 1000W output each
Internal Storage :
Each Jetson Orin module has its own M.2 NVMe interface
Dimensions :
Standard 2U rackmount height (3.5 inch / 88.9mm), 25 inch / 635mm depth
Products & Services
Anvil-RX Rugged System Powered by NVIDIA Jetson AGX Orin
Connect Tech
Anvil-RX takes rugged AI and high compute performance to new heights.
Connect Tech’s Anvil-RX is a rugged embedded system powered by the NVIDIA® Jetson AGX Orin™. Fully IP67 rated, with M12 and sealed PC connectors, this powerful edge system can be deployed for mission critical applications in harsh environments. The Anvil-RX is ideal for AMR, robotics, agriculture, and industrial applications.
Connect Tech’s Anvil-RX is a rugged embedded system powered by the NVIDIA® Jetson AGX Orin™. Fully IP67 rated, with M12 and sealed PC connectors, this powerful edge system can be deployed for mission critical applications in harsh environments. The Anvil-RX is ideal for AMR, robotics, agriculture, and industrial applications.
Sentry-X2 MIL-Rugged System Powered by NVIDIA Jetson AGX Orin Industrial
Connect Tech
Sentry-X2 is a MIL-Rugged system, powered by the NVIDIA® Jetson AGX Orin™ Industrial module.
Designed for mission critical applications in harsh environments, the Sentry-X2 is a MIL-SPEC certified AI system for computing at the tactical edge. The NVIDIA® Jetson AGX Orin™ Industrial is a 2048-core GPU capable of 248 TOPS, ideal for advanced AI and machine learning applications. The Sentry-X2 includes 4x 3G-SDI/HD-SDI/SDI inputs and 2x 3G-SDI/HD-SDI/SDI outputs, suitable for complex vision systems, as well as 10Gb, 2.5Gb, and 1Gb Ethernet, dual USB 3.2 ports, and a wide array of I/O options.
Tested to MIL-STD specifications for shock and vibration and utilizing IP67 rated D38999 connectors for data integrity, Sentry-X2 is designed to meet the strict requirements of military, aerospace, and heavy industrial applications.
Environmental: MIL-STD-810H, DO-160H
EMC/EMI: MIL-STD-461G, MIL-HDBK-704F, MIL-HDBK-831
Designed for mission critical applications in harsh environments, the Sentry-X2 is a MIL-SPEC certified AI system for computing at the tactical edge. The NVIDIA® Jetson AGX Orin™ Industrial is a 2048-core GPU capable of 248 TOPS, ideal for advanced AI and machine learning applications. The Sentry-X2 includes 4x 3G-SDI/HD-SDI/SDI inputs and 2x 3G-SDI/HD-SDI/SDI outputs, suitable for complex vision systems, as well as 10Gb, 2.5Gb, and 1Gb Ethernet, dual USB 3.2 ports, and a wide array of I/O options.
Tested to MIL-STD specifications for shock and vibration and utilizing IP67 rated D38999 connectors for data integrity, Sentry-X2 is designed to meet the strict requirements of military, aerospace, and heavy industrial applications.
Environmental: MIL-STD-810H, DO-160H
EMC/EMI: MIL-STD-461G, MIL-HDBK-704F, MIL-HDBK-831
Polaris Embedded System with NVIDIA Jetson Orin NX
Connect Tech
Harnessing the Jetson Orin™ NX and built for robotics, smart city and autonomous machines, the rugged Polaris system provides a wide range of connectivity in an IP67 rated rugged package.
Polaris is ideal for deployable computer vision and deep learning applications in rugged environments.
Polaris is ideal for deployable computer vision and deep learning applications in rugged environments.
Graphite VPX Powered by NVIDIA Jetson AGX Orin Industrial
Connect Tech
The Graphite VPX is a rugged 3U VPX single board computer designed with the NVIDIA® Jetson AGX Orin™. Aligned to the Sensor Open Systems Architecture (SOSA) standard, it ensures seamless interoperability with SOSA-aligned systems.
Equipped with complete IPMI support, the Graphite VPX enables efficient remote management and monitoring capabilities. High-speed connectivity such as dual 10GBASE-KR Ethernet, dual USB 3.2 Gen2 and PCIe x8 Gen4 allow for ample expansion and integration. Meeting MIL-STD-810H and DO-160 for shock and vibration, it is an ideal choice for today’s mission-critical aerospace and defense AI applications.
Equipped with complete IPMI support, the Graphite VPX enables efficient remote management and monitoring capabilities. High-speed connectivity such as dual 10GBASE-KR Ethernet, dual USB 3.2 Gen2 and PCIe x8 Gen4 allow for ample expansion and integration. Meeting MIL-STD-810H and DO-160 for shock and vibration, it is an ideal choice for today’s mission-critical aerospace and defense AI applications.
People
Description
GPU-Accelerated Machine Learning and Inferencing Servers Bring Flexibility and Cost Efficiency to High-Powered Computing.
Developed in partnership with USES Integrated Solutions, the Inference Server is an extremely low-wattage, high-performance AI workstation powered by the NVIDIA Jetson Orin series.
Choose from the NVIDIA Jetson AGX Orin version with 12x 64GB modules or the Jetson Orin NX version with 24x 16GB modules. Running NVIDIA’s most powerful deep-learning software libraries, this inference server solves the challenge of deploying edge solutions at scale. The on-board Jetson Orin modules are all connected by a Gigabit Ethernet fabric through a specialized Managed Ethernet Switch with 10G uplink capability.
Developed in partnership with USES Integrated Solutions, the Inference Server is an extremely low-wattage, high-performance AI workstation powered by the NVIDIA Jetson Orin series.
Choose from the NVIDIA Jetson AGX Orin version with 12x 64GB modules or the Jetson Orin NX version with 24x 16GB modules. Running NVIDIA’s most powerful deep-learning software libraries, this inference server solves the challenge of deploying edge solutions at scale. The on-board Jetson Orin modules are all connected by a Gigabit Ethernet fabric through a specialized Managed Ethernet Switch with 10G uplink capability.
