Inter in AI on Edge Devicies

ARQUIMEA, we are a technology company operating globally and providing innovate solutions and products in highly demanding sectors.

Our areas of activity are Aerospace, Defense & Security, Big Science, Biotechnology and Fintech.  

ARQUIMEA Research Center (ARC), part of ARQUIMEA , was born in 2019 with the aim of inventing the technologies of tomorrow. An environment of innovation and excellence at European level from which senior and junior researchers from around the world develop disruptive technologies and business models that will serve as an engine of socio-economic growth in the medium and long term. 

We’re looking for candidates with a bachelor’s degree in engineering or computer science who are currently pursuing a master’s degree in a field related to artificial intelligence.

This internship offers the chance to engage with these challenges firsthand. Through hands-on work with cutting-edge hardware and model optimization techniques, you’ll contribute to the development of more efficient, robust, and portable AI solutions for deployment at the edge.

Internship Scope:

• Benchmark Edge AI Hardware Acceleration Platforms (2–3 months)
  Explore the capabilities and trade-offs of leading AI acceleration platforms. You'll deploy state-of-the-art neural network architectures, run edge-optimized models, and benchmark performance across various hardware solutions. This will provides crucial insights into how different platforms handle real-world AI workloads, helping to guide decisions for specific edge applications.
• Contribute to Cross-Platform Quantization Solutions (2–3 months)Dive into the challenges of quantization for edge AI. Contribute to the research of new methodologies to develop strategies to decouple quantization from hardware-specific tools, enabling more flexible and efficient model deployment across platforms. Your work will support more robust and cost-effective AI applications in real-world edge scenarios.

What You’ll Learn:

• How edge AI systems work and what makes them unique.
• Deployment of deep learning models on real embedded hardware.
• Evaluation of performance and efficiency trade-offs.
• Challenges and innovations in model quantization and compression.

Required Skills:

• Background in deep learning concepts and frameworks.
• Comfortable working with Python.
• Solid analytical and problem-solving abilities.
• A proactive attitude and the ability to work independently when needed

Nice-to-Have Skills

• Familiarity with Docker and containerization.
• Background in IoT or embedded systems.
• Understanding of neural network optimization and compression techniques.

* Please apply only if you are eligible to sign an internship agreement between your university and ARQUIMEA.

Think Big, Do the Job & Enjoy Life

At ARQUIMEA, we value diversity and inclusion. We do not discriminate on the basis of race, color, religion, gender, sexual orientation, gender identity, national origin, age, disability, or other protected factors by law. All candidates will be considered equally based on their skills and experience