Descripción de la oferta
pbCompany Description: /b /ppbr/ppAistech Space is focused on generating affordable, recurrent, high resolution thermal imagery of the planet to provide a new perspective of Earth’s changing resources. The company is based in Barcelona and aims to revolutionize remote sensing for environmental monitoring and resource management. /ppbr/ppAistech Space is seeking a highly specialized Machine Learning and Embedded AI Systems Engineer to serve as the critical bridge between data science, software, and hardware development. This role is focused on the successful integration and performance optimization of ML models across diverse and often constrained operational environments, including in-orbit systems (satellites, embedded TPUs), on-ground processing, and online platforms. The successful candidate will drive the deployment lifecycle, ensuring our AI systems are reliable and performant across the entire Aistech Space ecosystem. /ppbr/ppbr/ppbKey Responsibilities: /b /ppbr/pullibEmbedded Deployment: /b Collaborate with FPGA hardware, embedded software, and data science teams to deploy AI solutions directly onto satellites and other constrained Edge AI devices. /lilibAlgorithm Conversion: /b Implement high-performance solutions by transferring and optimizing algorithms initially created in Python into robust C/C++ codebases. /lilibInfrastructure Development: /b Research, recommend, and implement new hardware and software solutions to improve the company’s overall AI infrastructure. /lilibPerformance Optimization: /b Ensure AI models are highly optimized for efficiency, especially when utilizing hardware accelerators like GPUs and NPUs. /lilibTeam Support: /b Provide computational and deployment support to the Remote Sensing and Data Science teams. /li /ulpbr/ppbWho you are /b: /ppbr/ppbMust: /b /ppbr/pulliMasters/PhD in Computer Science, Engineering, or a related technical field. /liliFluency in English. /liliMore than 2 years of professional experience in Embedded Software Development. /liliProgramming fluency in C, C++, and Python. /liliProficiency with Linux environments and collaborative development using GitHub. /liliExperience with hardware acceleration technologies, including Graphics Processing Units (GPUs) and Neural Processing Units (NPUs). /liliExpertise in ML/Deep Learning deployment frameworks, such as TensorFlow Lite, ONNX Runtime, or PyTorch Edge. /liliWorking knowledge of MLOps principles for training/evaluation pipelines and automated model delivery/monitoring. /li /ulpbr/ppCritical bonus skills (high priority) /ppbr/pulliExperience with AMD Versal AI engines and Vitis Model Composer (Kernel development, data flow optimization, model quantization/pruning, Vitis IDE, and performance analysis are a plus). /liliExperience deploying models via web services, dashboards, and APIs (e.g., FastAPI, Flask, gRPC) and using cloud services/containerization (GCP, AWS, Azure, Docker, Kubernetes). /liliFamiliarity with High-Performance Computing (HPC) and job scheduling systems like SLURM. /li /ulpbr/ppbNice to have: /b /ppbr/pulliFamiliarity with containerization on constrained systems (e.g., Singularity, microcontainers). /liliKnowledge of data compression techniques for in-orbit data handling. /liliPrior experience in the aerospace or remote sensing industries. /li /ulpbr/ppbWhat You’ll Gain by Joining Us /b /p
