PstrongEdge Deployment Engineer (AI Embedded Systems) /strong strong| AI Start-up | fixed-term Contract /strong /ppbr/ppstrongJoin a European deep-tech leader in quantum and AI. /strong /ppbr/ppA well-funded, fast-growing company backed by major global investors with its groundbreaking technology is already transforming AI, compressing large language models by up to 95% and cutting inference costs by 50–80%. /ppThis is your chance to be part of a team often described as a strong“quantum-AI unicorn in the making.” /strong /ppbr/ppstrongThis is a Hybrid opportunity in Zaragoza. It is a fixed-term contract to work until 30th June 2026 /strong /ppbr/ppstrongWhat You'll Do: /strong /ppAs an Edge Deployment Engineer, you will be instrumental in bridging the gap between cutting-edge AI research and efficient, real-world execution. You will specialise in optimising and deploying highly compressed Machine Learning and Large Language Models onto resource-constrained, low-latency devices. /ppbr/ppstrongAs a Quality Control Engineer, you will: /strong /pulliImplement and optimise deep-learning models for edge hardware. /liliReduce model size and latency using compression/quantisation. /liliWork hands-on with embedded systems and systems programming. /liliUtilise key inference optimisation frameworks (e.g., TensorRT, vLLM). /liliWrite high-performance code in Python, C, or C++. /liliConduct performance profiling on diverse embedded architectures (ARM, GPUs). /liliIntegrate ML models into final products through team collaboration. /liliMaintain development standards: Git, testing, and CI/CD pipelines. /li /ulpbr/ppstrongRequired Qualifications /strong /pulliBachelor’s degree or higher in Computer Science, Electrical Engineering, Physics, or related field; or equivalent industry experience /lili3–5 years of hands-on experience in embedded systems, firmware development, or systems programming /liliDemonstrated experience optimizing machine learning models for deployment on constrained devices /liliStrong proficiency in Python, C, or C++; experience with system-level programming languages is essential /liliSolid understanding of quantization techniques and model compression strategies Experience with inference optimization frameworks (TensorRT, ONNX Runtime, LLM, vLLM, or equivalent) /liliFamiliarity with embedded architectures: ARM processors, mobile GPUs, and AI accelerators /liliStrong fundamentals in computer architecture, memory management, and performance optimization /liliExperience with version control (Git), testing frameworks, and CI/CD pipelines /liliExcellent communication and collaboration skills in cross-functional teams /li /ulpbr/ppstrongPreferred Qualifications /strong /pulliMaster’s degree in Computer Science, Electrical Engineering, or related field /liliHands-on experience with large language model inference and deployment /liliExperience optimizing neural networks using mixed-precision computation or dynamic quantization /liliFamiliarity with edge computing frameworks such as NVIDIA’s Triton Inference Server or similar platforms /liliBackground in mobile or IoT development /liliKnowledge of hardware acceleration techniques and specialized instruction sets (SIMD, NPU-specific optimizations) /liliContributions to open-source embedded AI or ML optimization projects /liliExperience with real-time operating systems or embedded Linux environments /li /ulpbr/ppstrongPerks Benefits: /strong /pullistrongCompensation: /strong Competitive salary, with a signing bonus and a retention bonus at the end of the contract. /lilistrongFlexibility: /strong This is a hybrid role with flexible working hours. A relocation package is available if needed. /lilistrongCulture: /strong We are a fast-scaling company committed to equal pay, diversity, and an inclusive culture. You'll gain international exposure in a multicultural, cutting-edge environment. /li /ulpbr/ppstrongInterested? Apply directly through LinkedIn, or send your CV to /strong /ppbr/ppemBy applying to this role you understand that we may collect your personal data and store and process it on our systems. For more information please see our Privacy Notice /em /p