Edge AI/Model Optimization Engineer

Location: Aberdeen, Maryland, United States; Workplace: Hybrid

Company

hirify.global provides advanced software solutions and professional services for mission and business support, including the ReadiChat agentic AI platform.

What you will do

• Evaluate, tune, benchmark, and operationalize LLMs, embedding models, and inference services on GPU-enabled edge platforms, including the X9 Spider Mission Computer.
• Optimize quantization, batching, context windows, caching, inference scheduling, and GPU memory utilization for constrained hardware.
• Benchmark agentic AI workflows, inference pipelines, and model-serving architectures against latency, throughput, reliability, and resource constraints.
• Package, deploy, validate, troubleshoot, and sustain local model-serving components in tactical, airborne, edge, and disconnected environments.
• Build repeatable performance and stress-testing frameworks covering failover, degraded resources, tool-call overhead, and disconnected operations.
• Collaborate with AI engineers, systems integrators, mission stakeholders, and operational users; train technical personnel and maintain deployment and optimization documentation.

Requirements

• Bachelor’s degree in Computer Science, Electrical Engineering, Computer Engineering, Data Science, Artificial Intelligence, or a related technical discipline.
• 5+ years of experience in AI/ML deployment, model optimization, edge computing, GPU acceleration, or AI inference operations.
• Experience deploying and optimizing LLMs, embedding models, or inference pipelines in resource-constrained environments.
• Experience with GPU-enabled systems and inference technologies such as CUDA, TensorRT, ONNX Runtime, vLLM, Ollama, or equivalent platforms.
• Experience with Linux, Docker, Kubernetes, Python, AI/ML deployment frameworks, benchmarking, and runtime performance optimization.
• Active security clearance is required.

Nice to have

• Experience with tactical, airborne, mission-command, or DDIL environments.
• Familiarity with X9 Spider or similar embedded GPU-enabled mission systems and operational AI ecosystems.
• Experience with INT8, FP16, GGUF, GPTQ, AWQ, or similar model quantization approaches.
• Experience conducting hardware evaluations and performance trade studies for edge compute systems.

Culture & Benefits

• Full-time employment in a hybrid work environment.
• Work focused on operational AI capabilities and mission-supporting technologies.
• Culture emphasizing fairness, respect, accountability, adaptability, and employee contributions.
• Environment that encourages participation at all levels, innovation, and responsible risk-taking.