Edge AI Architect: LLM & Inference Optimization

NextGen Federal Systems; Aberdeen (WA); On-site; USD 130,000 - 190,000; Full time

Job summary

NextGen Federal Systems seeks an Edge AI/Model Optimization Engineer to deploy, optimize, and sustain AI capabilities in edge and tactical computing environments. You will evaluate LLMs and embedding models for latency, memory usage, and reliability on constrained hardware such as the X9 Spider Mission Computer.

You will tune runtime configurations, collaborate with stakeholders to assess mission requirements, and build robust benchmarks and validation procedures to ensure dependable AI

Qualifications

• Bachelor's degree in a technical field (CS/EE/CE/AI) or related discipline.
• 5+ years in AI/ML deployment, model optimization, edge computing, or AI inference operations.
• Experience deploying and optimizing LLMs or embeddings on constrained hardware.
• Proficiency with GPU-enabled systems and inference optimization tools (CUDA, TensorRT, ONNX Runtime).
• Experience tuning runtime configurations (quantization, batching, memory).
• Familiarity with Linux, containerized deployments (Docker/Kubernetes).
• Strong analytical, troubleshooting, and communication skills.
• Active Security Clearance required.

Responsibilities

• Evaluate LLMs and embedding models for quality, latency, memory, and reliability on edge-enabled platforms (X9 Spider).
• Tune runtime configurations for edge deployment including quantization, batching, and memory optimization.
• Collaborate with stakeholders to assess mission requirements and platform tradeoffs.
• Benchmark AI workflows and model-serving architectures against hardware constraints.
• Develop repeatable performance and stress-testing frameworks for edge environments.
• Package, deploy, and sustain local model-serving components for edge operations.
• Support integration teams to ensure mission effectiveness after optimizations.

Skills

AI model optimization

Edge computing

GPU acceleration

Linux

Python

Communication

Security clearance

Education

Bachelor's degree in Computer Science / Electrical Engineering or related

Tools

CUDA

TensorRT

ONNX Runtime

vLLM

Ollama

Job description

NextGen Federal Systems seeks an Edge AI/Model Optimization Engineer to deploy, optimize, and sustain AI capabilities in edge and tactical computing environments. You will evaluate LLMs and embedding models for latency, memory usage, and reliability on constrained hardware such as the X9 Spider Mission Computer.

You will tune runtime configurations, collaborate with stakeholders to assess mission requirements, and build robust benchmarks and validation procedures to ensure dependable AI