Edge AI/ML Engineer — Real-Time Wireless Inference on GPU

Aimlroles; Maryland; On-site; USD 99,000 - 225,000; Full time

Job summary

Booz Allen is seeking a Wireless and Edge AI/ML Engineer to build a converged platform for real-time wireless signal processing and AI inference on GPU hardware. You will design and optimize ML models, create data pipelines from network telemetry, and deploy containerized inference services on Kubernetes.

Responsibilities include benchmarking latency, integrating with the radio stack, and collaborating with RF and security teams to meet mission requirements in a lab environment.

Qualifications

• 3+ years of experience training and evaluating ML models using PyTorch or TensorFlow, including exporting to ONNX for deployment.
• 3+ years of Python development with production-quality code, testing, and version control.

Responsibilities

• Design, train, and evaluate ML models for wireless network use cases.
• Build data pipelines ingesting telemetry into training datasets.
• Optimize models for real-time edge inference on GPU-accelerated servers.
• Containerize inference services and deploy on Kubernetes with NVIDIA tools.
• Develop AI-driven network applications and validate end-to-end in lab.

Skills

PyTorch

TensorFlow

Python

CUDA

Kubernetes

Docker

Education

Bachelor's degree in STEM

Tools

NVIDIA Triton

ONNX Runtime

Job description

Booz Allen is seeking a Wireless and Edge AI/ML Engineer to build a converged platform for real-time wireless signal processing and AI inference on GPU hardware. You will design and optimize ML models, create data pipelines from network telemetry, and deploy containerized inference services on Kubernetes.

Responsibilities include benchmarking latency, integrating with the radio stack, and collaborating with RF and security teams to meet mission requirements in a lab environment.