Edge AI Engineer

Society of Defense Financial Management; Charlotte (NC); On-site; USD 120,000 - 180,000; Full time

Job summary

PowerusPowerus is seeking an Edge AI Engineer to deploy and validate ML models on embedded hardware for autonomous aerial systems. The role covers model conversion, quantization, and on-target inference pipelines, collaborating with autonomy and flight software teams.

You'll optimize performance with TensorRT/ONNX/CUDA, profile on-device metrics, and ensure robust deployment through HIL testing and documentation.

Qualifications

• Must have a Bachelor's degree in a related field or equivalent experience.
• Experience deploying ML models to embedded/edge hardware with C++/Python.
• Proficient in TensorRT, ONNX, and CUDA for optimization.
• Hands-on experience with PyTorch or TensorFlow and embedded Linux.
• U.S. Person status required for ITAR/EAR access.

Responsibilities

• Convert, optimize, and deploy trained models to embedded GPUs/accelerators (NVIDIA Jetson).
• Apply quantization (INT8/FP16) and pruning to meet latency and power targets.
• Build inference pipelines using TensorRT, ONNX Runtime, CUDA.
• Integrate inference with camera/sensor/flight software in C++/Python.
• Profile latency, throughput, memory, power, and thermal behavior on target hardware.
• Define acceptance criteria for deployed models and maintain QA tooling.
• Document deployment configs and interface specs; support HIL/flight tests.

Skills

C++

Python

TensorRT

ONNX

CUDA

PyTorch

TensorFlow

Embedded Linux

Education

Bachelor's degree in computer engineering / CS / EE

Tools

NVIDIA Jetson

JetPack

Job description

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.