S
Edge AI Engineer
Society of Defense Financial Management
5 hours ago
Full-time
On-site
Charlotte, North Carolina, United States
About the Company
About PowerusPowerus is building a next-generation American autonomous systems platform designed to move, protect, and sustain critical assets in high-consequence environments. The company combines advanced autonomy, manufacturing capability, operational expertise, and strategic acquisitions to support defense, national security, critical infrastructure, and commercial operations globally.
MissionOur mission is to deliver resilient autonomous technologies that strengthen national security, improve operational safety, and expand the capabilities of organizations operating in complex environments.
Why Join PowerusPowerus runs machine learning models on board its autonomous aerial systems for perception, target recognition, and navigation. Each platform carries a fixed compute, power, and thermal budget, and models must meet real-time latency requirements within that budget without a network connection.
About the Role This role owns the deployment of those models to embedded hardware. The position sits within the engineering organization and works directly with autonomy, avionics, and flight test engineering.
Position OverviewPowerus is seeking an Edge AI Engineer to optimize, deploy, and validate machine learning models on embedded compute aboard autonomous aerial systems. The role covers model conversion and quantization, inference runtime integration, on-target profiling, and flight validation of onboard AI functions.
Responsibilities
Key Responsibilities
Convert, optimize, and deploy trained models to embedded GPU and accelerator platforms, including NVIDIA Jetson
Apply quantization, pruning, and layer fusion to meet latency, memory, and power targets
Build and maintain inference pipelines using TensorRT, ONNX Runtime, and CUDA
Integrate inference pipelines with camera, sensor, and flight software interfaces in C++ and Python
Profile on-target performance, including latency, throughput, memory, power draw, and thermal behavior
Define and maintain accuracy and performance acceptance criteria for deployed models
Develop tooling for repeatable model build, benchmarking, and deployment to target hardware
Support hardware-in-the-loop (HIL) and flight testing of onboard AI functions; analyze flight data and resolve field issues
Advise on compute hardware selection for new platforms and payloads
Document model deployment configurations, performance results, and interface definitions
Qualifications
QualificationsMust be located in the United States, within commuting distance of Charlotte, NC
Bachelor's degree in computer engineering, computer science, electrical engineering, or a related discipline, or equivalent practical experience
Professional experience deploying machine learning models to embedded or edge hardware
Proficiency in C++ and Python
Experience with TensorRT, ONNX, or equivalent inference optimization toolchains
Experience with CUDA or GPU performance profiling
Working knowledge of deep learning frameworks such as PyTorch or TensorFlow
Experience with model quantization (INT8/FP16) and its effect on accuracy
Experience with embedded Linux development
U.S. Person status required (U.S. citizen, lawful permanent resident, or protected individual under 8 U.S.C. 1324b(a)(3)); this role involves access to ITAR- and EAR-controlled technical data
Required Skills
Professional experience deploying machine learning models to embedded or edge hardware
Proficiency in C++ and Python
Experience with TensorRT, ONNX, or equivalent inference optimization toolchains
Experience with CUDA or GPU performance profiling
Working knowledge of deep learning frameworks such as PyTorch or TensorFlow
Experience with model quantization (INT8/FP16) and its effect on accuracy
Experience with embedded Linux development
Preferred Skills
Preferred QualificationsExperience with NVIDIA Jetson platforms and JetPack
Experience deploying computer vision models for object detection, tracking, or segmentation
Experience with GStreamer, DeepStream, or real-time video pipelines
Experience with ROS 2 or flight software integration
Experience on unmanned aerial systems (UAS) or other size-, weight-, and power-constrained platforms
Experience with FPGA or dedicated AI accelerator deployment
Active or prior U.S. security clearance
What We Look ForThe right candidate has taken a trained model to production on embedded hardware and met a hard latency or power requirement in the process. Experience diagnosing performance or accuracy regressions on target hardware, rather than in simulation only, is the differentiator.
Equal Opportunity Statement Equal Opportunity StatementPowerus is an equal opportunity employer committed to building a diverse and mission-driven workforce. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, or any other characteristic protected by applicable law.
#J-18808-Ljbffr
MissionOur mission is to deliver resilient autonomous technologies that strengthen national security, improve operational safety, and expand the capabilities of organizations operating in complex environments.
Why Join PowerusPowerus runs machine learning models on board its autonomous aerial systems for perception, target recognition, and navigation. Each platform carries a fixed compute, power, and thermal budget, and models must meet real-time latency requirements within that budget without a network connection.
About the Role This role owns the deployment of those models to embedded hardware. The position sits within the engineering organization and works directly with autonomy, avionics, and flight test engineering.
Position OverviewPowerus is seeking an Edge AI Engineer to optimize, deploy, and validate machine learning models on embedded compute aboard autonomous aerial systems. The role covers model conversion and quantization, inference runtime integration, on-target profiling, and flight validation of onboard AI functions.
Responsibilities
Key Responsibilities
Convert, optimize, and deploy trained models to embedded GPU and accelerator platforms, including NVIDIA Jetson
Apply quantization, pruning, and layer fusion to meet latency, memory, and power targets
Build and maintain inference pipelines using TensorRT, ONNX Runtime, and CUDA
Integrate inference pipelines with camera, sensor, and flight software interfaces in C++ and Python
Profile on-target performance, including latency, throughput, memory, power draw, and thermal behavior
Define and maintain accuracy and performance acceptance criteria for deployed models
Develop tooling for repeatable model build, benchmarking, and deployment to target hardware
Support hardware-in-the-loop (HIL) and flight testing of onboard AI functions; analyze flight data and resolve field issues
Advise on compute hardware selection for new platforms and payloads
Document model deployment configurations, performance results, and interface definitions
Qualifications
QualificationsMust be located in the United States, within commuting distance of Charlotte, NC
Bachelor's degree in computer engineering, computer science, electrical engineering, or a related discipline, or equivalent practical experience
Professional experience deploying machine learning models to embedded or edge hardware
Proficiency in C++ and Python
Experience with TensorRT, ONNX, or equivalent inference optimization toolchains
Experience with CUDA or GPU performance profiling
Working knowledge of deep learning frameworks such as PyTorch or TensorFlow
Experience with model quantization (INT8/FP16) and its effect on accuracy
Experience with embedded Linux development
U.S. Person status required (U.S. citizen, lawful permanent resident, or protected individual under 8 U.S.C. 1324b(a)(3)); this role involves access to ITAR- and EAR-controlled technical data
Required Skills
Professional experience deploying machine learning models to embedded or edge hardware
Proficiency in C++ and Python
Experience with TensorRT, ONNX, or equivalent inference optimization toolchains
Experience with CUDA or GPU performance profiling
Working knowledge of deep learning frameworks such as PyTorch or TensorFlow
Experience with model quantization (INT8/FP16) and its effect on accuracy
Experience with embedded Linux development
Preferred Skills
Preferred QualificationsExperience with NVIDIA Jetson platforms and JetPack
Experience deploying computer vision models for object detection, tracking, or segmentation
Experience with GStreamer, DeepStream, or real-time video pipelines
Experience with ROS 2 or flight software integration
Experience on unmanned aerial systems (UAS) or other size-, weight-, and power-constrained platforms
Experience with FPGA or dedicated AI accelerator deployment
Active or prior U.S. security clearance
What We Look ForThe right candidate has taken a trained model to production on embedded hardware and met a hard latency or power requirement in the process. Experience diagnosing performance or accuracy regressions on target hardware, rather than in simulation only, is the differentiator.
Equal Opportunity Statement Equal Opportunity StatementPowerus is an equal opportunity employer committed to building a diverse and mission-driven workforce. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, or any other characteristic protected by applicable law.
#J-18808-Ljbffr