Edge Compute Systems Engineer

Vantor is forging the new frontier of spatial intelligence, helping decision makers and operators navigate what’s happening now and shape what’s coming next. Vantor is a place for problem solvers, changemakers, and go-getters—where people are working together to help our customers see the world differently, and in doing so, be seen differently. Come be part of a mission, not just a job, where you can:
Shape your own future, build the next big thing, and change the world.

To be eligible for this position, you must be a U.S. Person, defined as a U.S. citizen, permanent resident, Asylee, or Refugee.

Export Control/ITAR:
Certain roles may be subject to U.S. export control laws, requiring U.S. person status as defined by 8 U.S.C. 1324b(a)(3).

Please review the job details below.

Vantor is currently seeking a Staff Edge Compute Systems Engineer to join our Space Wrx Engineering team in Westminster, CO.

Our team within the Space Wrx organization is responsible for defining and managing the design, development, and deployment of resilient, autonomous space systems that push advanced computation and AI closer to where data is generated: on-orbit.

We are seeking a senior Edge Compute Engineer fluent in embedded software, compute hardware, and on-orbit AI/ML integration. This role plays a central part in the full lifecycle of onboard processing — from architecture and hardware selection, through integration, deployment, and operational performance.

You will work at the intersection of:

• High-performance embedded software
• Compute hardware architecture
• Satellite interfaces and avionics integration
• Edge AI and real-time processing

• Contribute to the architecture and development of Vantor’s GPU-accelerated onboard compute platform through flight deployment.
• Help guide technical direction for NVIDIA-based embedded systems, balancing performance, power, reliability, and scalability.
• Design and optimize GPU-accelerated compute stacks for on-orbit AI/ML inference under strict spaceflight constraints.
• Develop high-performance C/C++ and GPU-accelerated components where efficiency is mission-critical.
• Lead full-stack performance optimization, including memory management, model acceleration, quantization, and runtime tuning.
• Integrate compute subsystems with spacecraft avionics, sensors, radios, and command/telemetry systems.
• Contribute to system bring-up, hardware-in-the-loop validation, profiling, and flight-representative testing.
• Design for reliability, fault tolerance, and autonomous operation in constrained or degraded environments.
• Evaluate emerging onboard processing approaches and applications and determine which warrant system-level integration.
• Deliver production-grade systems ready for operational deployment.

• Must be a U.S. citizen and possess, or have the ability to obtain, a U.S. Government Secret security clearance.
• Bachelor’s or Master’s degree in Computer Science, Electrical/Computer Engineering, Systems Engineering, or equivalent experience.
• Significant experience developing software for space, aerospace, or other mission-critical embedded systems.
• Strong C/C++ expertise for performance-critical, real-time systems.
• Experience optimizing software in resource-constrained environments (power, thermal, memory, latency).
• Experience with Linux-based embedded platforms, cross-compilation, debugging, and performance tuning.
• Strong understanding of compute architectures (memory hierarchy, concurrency, scheduling, hardware acceleration).
• Experience deploying or optimizing AI/ML inference workloads in embedded or edge environments.
• Familiarity with spacecraft or aerospace subsystem interfaces (e.g., Space Wire, CAN, Ethernet, PCIe, telemetry/command architectures).
• Ability to operate independently, communicate architectural decisions clearly, and drive technically complex initiatives with minimal oversight.
• Proven ability to collaborate effectively across multidisciplinary engineering teams.

• Experience with NVIDIA GPUs or GPU-accelerated systems (CUDA a plus).
• Familiarity with AI/ML inference acceleration frameworks (Tensor
  
  RT, ONNX Runtime, or similar).
• Exposure to radiation-aware…