Edge AI Optimization Engineer for Tactical Systems

Nextgenfed; Aberdeen (MD); On-site; USD 140,000 - 210,000; Full time

Job summary

NextGen is seeking a skilled Edge AI/Model Optimization Engineer to support deployment, optimization, and sustainment of AI capabilities on edge and tactical computing platforms. You will evaluate, tune, benchmark, and operationalize large language models and embedding models for constrained hardware such as the X9 Spider Mission Computer architecture.

The role requires collaboration with AI engineers, systems integrators, and mission stakeholders to ensure AI-enabled capabilities stay

Qualifications

• Bachelor's degree in a technical discipline.
• 5+ years of AI/ML deployment and edge computing experience.
• Experience deploying LLMs and AI inference in constrained environments.
• Familiarity with CUDA, TensorRT, ONNX Runtime, or equivalent.
• Experience tuning runtime configurations (quantization, batching, memory).
• Proven ability to benchmark AI workloads on edge hardware.
• Proficiency with Linux, containers, and orchestration tools.

Responsibilities

• Evaluate LLMs and AI inference solutions for quality, latency, and memory on embedded GPUs.
• Tune runtime configurations for edge deployment and hardware constraints.
• Collaborate with stakeholders to assess mission requirements and platform tradeoffs.
• Benchmark workflows and model-serving architectures against hardware limits.
• Recommend model selection and runtime tradeoffs for mission effectiveness.
• Develop repeatable performance, stress tests, and deployment validation workflows.
• Package, deploy, and sustain local model-serving components for edge environments.
• Coordinate with engineering and integration teams to ensure reliable agent behavior after optimizations.
• Support edge deployments in tactical or disconnected environments.
• Train customer personnel on supported profiles, constraints, and sustainability practices.
• Maintain documentation and benchmarking results.

Skills

AI model optimization

Edge computing

GPU acceleration

Python

Linux & containers

CI/CD

Education

Bachelor's degree in CS/Engineering

Tools

CUDA

TensorRT

ONNX Runtime

vLLM

Docker

Kubernetes

Job description

NextGen is seeking a skilled Edge AI/Model Optimization Engineer to support deployment, optimization, and sustainment of AI capabilities on edge and tactical computing platforms. You will evaluate, tune, benchmark, and operationalize large language models and embedding models for constrained hardware such as the X9 Spider Mission Computer architecture.

The role requires collaboration with AI engineers, systems integrators, and mission stakeholders to ensure AI-enabled capabilities stay