Edge AI Optimization Engineer — LLMs & Inference

Artha Nexgen; San Francisco, Northern (CA, KY); Hybrid; USD 120,000 - 190,000; Full time

Job summary

NextGen Federal Systems seeks an Edge AI/Model Optimization Engineer to support deployment and sustainment of AI capabilities in edge and tactical environments. You will evaluate, tune, benchmark, and operationalize LLMs and embedding models for constrained hardware including edge compute systems, ensuring performance under degraded and low-bandwidth conditions.

The role requires collaboration with AI engineers, systems integrators, and mission stakeholders to optimize model performance,

Qualifications

• 5+ years experience deploying ML/AI on edge or constrained hardware.
• Experience optimizing LLMs or embedding models for edge environments.
• Proficient with CUDA, TensorRT, ONNX Runtime or equivalent.
• Experience with Linux-based systems and container orchestration.
• Ability to communicate complex tech tradeoffs to stakeholders.
• Active Security Clearance required.

Responsibilities

• Evaluate LLMs and embedding models for quality, latency, and memory usage on edge platforms.
• Tune runtime configurations, quantization, batching, and memory strategies.
• Benchmark AI workflows against hardware constraints and operational thresholds.
• Collaborate with stakeholders to assess mission requirements and platform options.
• Package, deploy, and sustain local model-serving components for edge environments.
• Develop repeatable performance and stress-testing frameworks.

Skills

5+ years experience

Edge AI

Model optimization

GPU acceleration

Linux

Python

Docker/Kubernetes

CUDA/TensorRT/ONNX

Experimentation/benchmarking

Communication with stakeholders

Security clearance

Education

Bachelor's degree in CS/EE/CE/Data Science/AI

Tools

CUDA

TensorRT

ONNX Runtime

vLLM

Ollama

Docker

Kubernetes

Job description

NextGen Federal Systems seeks an Edge AI/Model Optimization Engineer to support deployment and sustainment of AI capabilities in edge and tactical environments. You will evaluate, tune, benchmark, and operationalize LLMs and embedding models for constrained hardware including edge compute systems, ensuring performance under degraded and low-bandwidth conditions.

The role requires collaboration with AI engineers, systems integrators, and mission stakeholders to optimize model performance,