AI Systems Engineer (LLM & RAG Optimization)
Core
Optimizing the efficiency, scalability, and performance of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems for military avionics applications.
Role type
Senior Machine Learning Engineer (LLM Inference & RAG)
Builds
High-performance AI inference pipelines, RAG workflows, and optimized model serving infrastructure.
Domain
Defense & Space / Military Avionics / Generative AI
Deliverable
production ML models
Required skills
LLM deployment and productionization, RAG system architecture, multi-GPU high-performance management, Python, vector databases, data pipeline development, API design, model optimization (quantization, weight reduction), long-context window management, containerized environments (Kubernetes), air-gapped environment experience
Preferred skills
Military avionics and embedded/Real Time Software knowledge, large-scale model experience, model training and fine-tuning
Technologies
Python, Kubernetes, Vector Databases, GPU clusters
Responsibilities
Design and manage LLM deployment to optimize memory usage and responsiveness; Design and refine RAG workflows for accurate private information querying; Configure and optimize workload distribution across multiple GPUs; Implement evaluation methodologies to reduce hallucinations and improve response relevance; Create efficient processes for transforming complex documents into AI-optimized formats; Develop standardized and secure communication interfaces for AI integration; Research and prepare infrastructure for future model training and adaptation.
Seniority
Senior, hands-on IC