About this role
Edge AI/Model Optimization Engineer at Nextgenfed. Location: Aberdeen, Maryland, United States. Role: Evaluating models, Tuning runtimes, Collaborating stakeholders Requirements: Experience deploying ML on edge GPUs, optimizing LLMs, and performance tuning; requires security clearance. Category: Engineering Seniority: Senior Level Tools: CUDA, TensorRT, ONNX Runtime, vLLM, Ollama, Linux, Docker, Kubernetes, Python Commitment: Full Time Workplace: Hybrid Languages: English