December 2025
Job Title: Edge Deployment Engineer (AI & Embedded Systems) Location: Barcelona or Zaragoza, Spain (hybrid; some fully remote/onsite options elsewhere) Company Type: Deep-tech startup, AI/quantum firm, or multinational tech/engineering company Employment Type: Full-time or fixed-term contract (e.g., to June 2026 in some cases) Salary Range (indicative for Spain 2026): €55,000–€90,000+ base (higher for senior/experienced; relocation/visas often available for international talent)
About the Role We are seeking an Edge Deployment Engineer to optimize and deploy high-performance AI/ML models on resource-constrained edge devices, enabling real-time, low-power intelligence in decentralized environments. You will bridge the gap between AI research/prototyping and efficient, reliable execution focusing on model compression, hardware acceleration, embedded integration, and production deployment. This role is ideal for engineers passionate about edge computing, embedded AI, and bringing cutting-edge models (including LLMs or vision models) to life on devices with strict constraints (power, memory, latency).
Key Responsibilities
- Optimize, quantize, prune, and compress AI/ML models (e.g., using TensorFlow Lite, ONNX Runtime, PyTorch Mobile, or custom tools) for deployment on edge hardware (e.g., ARM-based SoCs, NVIDIA Jetson, RISC-V, or neuromorphic chips).
- Develop and implement efficient inference pipelines, including real-time processing, adaptive compute, and on-device adaptation/federated learning where applicable.
- Deploy models to edge devices: build deployment scripts, CI/CD pipelines for edge updates, over-the-air (OTA) mechanisms, and integration with embedded firmware/OS.
- Profile, benchmark, and debug runtime performance on actual hardware addressing issues like latency, power consumption, thermal throttling, and reliability under real-world conditions.
- Collaborate with AI researchers, embedded software engineers, and hardware teams to define requirements, select accelerators, and ensure seamless end-to-end workflows (from cloud training to edge inference).
- Design and automate testing/validation frameworks for edge deployments (accuracy validation, stress testing, edge-specific metrics like FPS/Watt).
- Integrate edge AI solutions with broader systems (e.g., cloud orchestration, 5G/LoRa connectivity, sensors, or secure boot mechanisms).
- Troubleshoot production issues, monitor deployed models, and implement retraining/rollback strategies for edge environments.
- Contribute to best practices, documentation, and tools for scalable edge AI deployment.
Required Qualifications
- 3–7+ years of experience in software/embedded engineering, with proven hands-on work deploying ML models to edge/embedded devices.
- Strong proficiency in Python (core), C/C++ (for embedded/performance-critical code), and ML frameworks (PyTorch, TensorFlow, ONNX).
- Experience with model optimization techniques (quantization, pruning, distillation, knowledge distillation) and runtime engines (TensorRT, TFLite, OpenVINO).
- Familiarity with embedded systems, Linux kernel/modules, cross-compilation, and hardware platforms (e.g., Raspberry Pi, Jetson, custom SoCs).
- Solid understanding of edge computing constraints (low power, limited memory/CPU, intermittent connectivity) and real-time systems.
- Bachelor’s or Master’s in Computer Science, Electrical Engineering, AI, Embedded Systems, or related field (PhD advantageous for research-heavy roles).
- Strong debugging, profiling, and problem-solving skills (tools like perf, Valgrind, gdb).
Preferred Skills / Nice-to-Haves
- Expertise in edge AI accelerators, neuromorphic computing, RISC-V, or low-power inference.
- Experience with MLOps/DevOps for edge (e.g., Docker for embedded, Kubernetes edge variants, Ansible for fleet management).
- Knowledge of generative AI/LLMs on edge (e.g., small/quantized models, on-device fine-tuning).
- Familiarity with secure deployment (encryption, secure boot, OTA security).
- Domain experience in IoT, robotics, autonomous systems, quantum-AI, or industrial edge applications.
- Open-source contributions or portfolio showing edge deployments.
What We Offer
- Work on groundbreaking edge AI projects with real-world impact (e.g., decentralized intelligence, low-latency applications).
- Collaborative environment in a growing deep-tech scene, with opportunities for innovation and events.
- Competitive compensation, flexible hybrid work, professional development, and potential relocation support.
How to Apply Submit your CV, cover letter, and relevant portfolio (e.g., GitHub repos with edge deployments) via the company careers page, LinkedIn, or direct email. Proactive applications are encouraged for unposted roles—reach out via contact forms highlighting your edge/embedded AI experience.
