Embedded Software Engineer

AI Optimisation Engineer/Embedded Software Engineer

We are currently partnered with a leading semiconductor and AI technology organisation in the Netherlands, seeking an Agentic & Generative Edge AI Optimisation Engineer to join their AI Competence Centre. The role focuses on optimizing large language and multimodal models for efficient deployment on edge AI platforms, including NPUs.

This is a 12-month contract based onsite in Eindhoven, Netherlands, with a minimum of 3 days per week.

About the role

In this position, you will work at the intersection of Generative AI, Agentic AI, and embedded edge deployment. Your focus will be on translating cutting-edge research into production-ready solutions, optimizing models for performance, compression, and safe agentic behaviour. You will collaborate with software and hardware teams to deliver high-impact AI features for NPU-based platforms.

Key responsibilities

• Optimize LLMs, multimodal models, and Vision-Language-Action models for on-device deployment
• Apply advanced quantization, pruning, and distillation techniques for optimized AI models
• Accelerate inference performance and develop system optimizations such as speculative decoding tailored for edge devices
• Engineer agentic AI capabilities for small language models and tiny agents at the edge, ensuring safety and policy guardrail

Key requirements

• MSc, PhD, or EngD in Computer Science, AI, Embedded Systems, or a related technical field
• 5+ years of experience in software/AI engineering, including deep exposure to LLMs, VLMs, and system performance
• Experience with LLM quantization techniques and pruning
• Strong track record with AI frameworks
• Experience with Agentic AI frameworks
• Knowledge of AI toolchains, deployment frameworks, and inference engines
• Experience with embedded systems, NPUs, and low-level software architecture
• Strong programming skills in C, C++, Python, Bash on Linux systems

Keywords:

Generative AI / Agentic AI / LLM / Multimodal AI / VLA Models / Edge AI / NPU / Model Optimization / Quantization / Pruning / Distillation / System Optimizations / Embedded AI / PyTorch / TensorFlow / ONNX / TFLite / Ollama / Linux / C++ / Python / Bash / ML-Ops / AI Deployment

If you are interested in this Edge AI Optimization Engineer position, please send a CV to [email protected]

By 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 https://eu-recruit.com/wp-content/uploads/2024/07/European-Tech-Recruit-Privacy-Notice-2024.pdf