Airbus Defence and Space SAU
Defence & Space
AISystemsEngineer(LLM&RAGOptimization)
Neural analysis suggests this role is
optimal for Professional candidates.
“AI Systems Engineer (LLM & RAG Optimization) at Airbus Defence and Space SAU. Skills: LLM Inference, RAG Optimization, Model Serving Optimization, High-performance system optimization, Python. Optimize the efficiency and scalability of Generative AI systems. Optimize the deployment and performance of Large Language Models (LLMs)”
What You'll Achieve.
Optimize the efficiency and scalability of Generative AI systems; Optimize the deployment and performance of Large Language Models (LLMs); Ensure that AI systems are fast, accurate, and capable of serving multiple simultaneous users; Lay the groundwork for future evolution toward training and fine-tuning open models; Squeeze the maximum potential out of hardware (GPUs) to deliver high-quality responses with the lowest possible latency; Maximize processing speed and user concurrency; Reduce hallucinations, improve response relevance; Ensure the AI is a reliable tool for the end user
Industry & Context.
Optimize the efficiency and scalability of Generative AI systems; Optimize the deployment and performance of Large Language Models (LLMs); Ensure that AI systems are fast, accurate, and capable of serving multiple simultaneous users; Squeeze the maximum potential out of hardware (GPUs) to deliver high-quality responses with the lowest possible latency; Optimize memory usage and responsiveness for high-demand environments; Refine RAG workflows; Maximize processing speed and user concurrency; Reduce hallucinations, improve response relevance; Create efficient processes for transforming complex documents; Develop standardized and secure communication interfaces; Research and prepare the infrastructure for future phases
Awareness of any potential compliance risks, Commitment to act with integrity, High-security (air-gapped) environments
What They're Looking For.
Must Have
Solid experience (3+ years) in Machine Learning Engineering, Natural Language Processing (NLP), or Applied AI, Degree in Computer, Telecomunications, Maths or Software Engineering, Hands-on experience in the deployment and productionization of Large Language Models (LLMs), Advanced proficiency in Python, Proven experience building information retrieval architectures (RAG systems) and vector databases, Demonstrated ability to optimize computing resources (GPU/CPU/Memory) to enhance AI system performance, B2 level in English
Nice to Have
Military Avionics and embedded/Real Time Software knowledge is desirable, Experience working with large-scale models, Knowledge of model optimization techniques (quantization, model weight reduction), Experience managing very large information contexts (long-context windows), Knowledge of containerized environments (Kubernetes) and high-security (air-gapped) environments, Previous experience in fine-tuning or training language models
What You'll Do.
Optimize the efficiency and scalability of Generative AI systems
Optimize the deployment and performance of Large Language Models (LLMs)
Ensure that AI systems are fast
and capable of serving multiple simultaneous users
Design and manage the deployment of Large Language Models (LLMs)
optimizing memory usage and responsiveness for high-demand environments
Design and refine RAG (Retrieval-Augmented Generation) workflows
Configure and optimize workload distribution across multiple GPUs to maximize processing speed and user concurrency
Implement evaluation methodologies to reduce hallucinations
improve response relevance
and ensure the AI is a reliable tool for the end user
Create efficient processes for transforming complex documents (PDF
etc.) into formats optimized for AI learning and querying
Develop standardized and secure communication interfaces to integrate AI capabilities with other applications and user platforms
Research and prepare the infrastructure for future phases involving training
and model adaptation to specific needs
How You'll Work.
Team & Collaboration
Join the Architecture & Integration team at CLAEX; Collaborate with other applications and user platforms
Full Job Description
****Job Description:**** Airbus Defence & Space is looking for an LLM Inference Engineer to optimize the efficiency and scalability of Generative AI systems. The selected candidate will join the Architecture & Integration team at CLAEX, in Torrejón de Ardoz Air Base, with the goal of optimizing the deployment and performance of Large Language Models (LLMs). Their mission will be to ensure that AI systems are fast, accurate, and capable of serving multiple simultaneous users, laying the groundwork for future evolution toward training and fine-tuning open models. We are looking for an ML Engineer with a hybrid focus on applied Artificial Intelligence and high-performance system optimization. We are not just looking for someone who uses models, but for an expert capable of "squeezing the maximum potential" out of hardware (GPUs) to deliver high-quality responses with the lowest possible latency. **Key Responsibilities** * Model Serving Optimization: Design and manage the deployment of Large Language Models (LLMs), optimizing memory usage and responsiveness for high-demand environments. * RAG (Retrieval-Augmented Generation) System Architecture: Design and refine workflows that enable AI to accurately query private information, managing everything from document ingestion to intelligent data retrieval. * Multi-GPU High-Performance Management: Configure and optimize workload distribution across multiple GPUs to maximize processing speed and user concurrency. * Quality and Accuracy Assurance: Implement evaluation methodologies to reduce hallucinations, improve response relevance, and ensure the AI is a reliable tool for the end user. * Data Pipeline Development: Create efficient processes for transforming complex documents (PDF, OCR, etc.) into formats optimized for AI learning and querying. * Service and API Exposure: Develop standardized and secure communication interfaces to integrate AI capabilities with other applications and user platforms. * Technological Evolution:
Applying for this AI Systems Engineer (LLM & RAG Optimization) role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Workday
- Workday has a multi-step form — save your progress after every section.
- "Apply With LinkedIn" can fail or lose data; manual entry is more reliable.
- Watch for the "Submit for Review" final step — hitting "Save" alone does not submit.
- Job requisition numbers are useful when following up with HR by email.
ANONYMOUS · UNFILTERED
What do employees actually say about Airbus Defence and Space SAU?
Real rants from real employees. Read before you apply.