Do you get excited about working with cutting-edge AI technologies? And do you want to make an impact in the rapidly evolving world of Generative AI and intelligent systems? At the same time, would you like to work for a company where both technology and personal development are central?

Then you might be the AI Engineer we are looking for.

What will you do as an Agentic & Generative Edge AI Optimization Engineer?

In this role, you will work on advanced AI systems that bring Generative AI capabilities to edge devices and embedded platforms. You will be part of an ambitious, multidisciplinary environment where AI research meets real-world applications.

Your focus will be on optimizing and deploying large language models and multimodal AI systems for resource-constrained environments, ensuring they run efficiently and reliably on specialized hardware accelerators.

Your responsibilities include:

Optimizing AI Models for Edge Deployment

• Optimize large language models (LLMs) and multimodal models for efficient on-device deployment.
• Apply advanced techniques such as quantization (8-bit, 4-bit, mixed precision), pruning, and distillation.
• Adapt models for execution on embedded AI accelerators and NPU-based platforms.

Accelerating AI Inference

• Investigate and implement system-level optimizations such as speculative decoding and efficient decoding algorithms.
• Improve performance, latency, and memory usage of AI systems in edge environments.

Engineering Agentic AI Systems

• Design and implement agentic AI capabilities, including tool orchestration and function calling.
• Explore techniques for enabling tiny agents on edge devices using small language models.
• Implement safe and reliable agent workflows, including guardrails and secure tool invocation.

Working with AI Inference and Deployment Frameworks

• Deploy optimized models using frameworks such as Ollama, llama.cpp, ONNX Runtime, and TensorFlow Lite.
• Ensure models run efficiently across different hardware platforms.

Benchmarking AI Systems

• Develop benchmarking pipelines to measure performance, efficiency, and reliability of Generative and Agentic AI systems running on-device.

Developing Proof-of-Concepts

• Build demonstrators and technology PoCs for edge AI use cases, such as intelligent sensing systems, industrial monitoring, or smart embedded applications.

From Research to Product

• Translate state-of-the-art AI research into production-ready implementations.
• Collaborate with multidisciplinary teams to integrate AI innovations into hardware and software platforms.

What we are looking for:

• MSc, EngD, or PhD in Computer Science, AI, Embedded Systems, or related field.
• 5+ years of experience in software or AI engineering with strong exposure to LLMs and multimodal systems.
• Strong experience with AI frameworks, such as PyTorch or TensorFlow.
• Hands-on experience with model optimization techniques, including:
• Quantization (e.g., SmoothQuant, SpinQuant, QuaRoT)
• Pruning (e.g., Wanda, SparseGPT)
• Efficient inference techniques

Agentic AI

• Experience with agent frameworks such as LangChain, Google ADK, SmolAgents, or similar.
• Knowledge of secure and safe agentic workflows (guardrails, policy enforcement, safe function calling) is a plus.

AI Deployment & Performance

• Familiarity with inference engines and toolchains such as:

CUDA

TensorRT

ONNX

TFLite

Ollama

Embedded Systems

• Strong affinity with embedded systems and hardware accelerators (NPUs).
• Experience working with embedded Linux environments and development boards.

Who are we?

Technology means progress. It is about continuously finding new ways to do things differently, improving products, services, and processes. That is what makes the heart of every technology organization and tech professional beat faster.

At ENTER, our professionals work on challenging projects together with leading high-tech partners. Every project is different, but they all have one thing in common: innovation through technology and the opportunity to grow as a professional.

We carefully match projects and engineers based on experience, ambition, personality, and passion for technology. Our Business Managers and Recruiters work closely together to ensure the right engineers are available for the right challenges at the right moment.

Within ENTER, we believe that technology is strongest when combined with the human touch.

#techwithaheartbeat

As a colleague at ENTER you can also expect from us

• A driven team and inspiring working environment where our motto #techwithaheartbeat is central.
• Passionate and enthusiastic colleagues.
• Salary range between 4500 and 6500.
• Plenty of room for personal growth and professional development.
• Challenging projects within leading high-tech environments.
• Regular social events such as the annual barbecue, Christmas dinner, pub quiz, and family day.
• An international working environment where you can grow by working on innovative projects and following specialized training programs.

Want to know more?

Do you want to know more about what you're going to do as Agentic & Generative Edge AI Optimization Engineer? Then contact Joris Buters thru email: [email protected]

Apply directly?

Are you so keen that you’d like to apply straight away?

If so, click the ‘Apply’ button and fill in your profile. We’ll get in touch with you as soon as possible.

By creating your profile and applying, you agree to our privacy statement.