Master Thesis Latency Estimation for DNN Optimization frameworks (f/m/x)

SOME IT WORKS. SOME CHANGES WHAT'S POSSIBLE.

SHARE YOUR PASSION.

More than 90% of automotive innovations are based on electronics and software. That's why creative freedom and lateral thinking are so important in the pursuit of truly novel solutions. That’s why our experts will treat you as part of the team from day one, encourage you to bring your own ideas to the table – and give you the opportunity to really show what you can do. 

We, the BMW Group, offer you an interesting and varied Master thesis in the area of efficient latency estimation for Network Architecture Search (NAS).

Accurately predicting the latency of neural architectures is a critical and challenging task in neural architecture design and search. Traditional approaches either depend on latency predictors limited to predefined design spaces or rely on Zero-Cost Proxies, which may lack accuracy. This thesis focuses on developing sample-efficient latency estimation methods, integrating neural architecture search (NAS) and network compression techniques to evaluate diverse architectures efficiently. The approach considers various factors such as model architecture, input size, and hardware characteristics, and leverages innovations in network representation and predictive modeling to ensure generalization to unseen architectures. By streamlining the construction of latency estimators, we aim to prevent them from becoming a bottleneck, thus facilitating the search for Hardware-aware neural architectures for efficient deployment.

What awaits you?

• Literature survey of state-of-the-art latency estimation methods focused on NAS and/or network compression techniques.
• Experience in implementing novel sample-efficient latency estimation methods and contributing to our PyTorch-based research stack.
• Engagement in a diverse team with experience in publishing at international peer-reviewed conferences.
• Scientific writing of your thesis and presentation of the research results both at the university and industry.

Please note that your thesis must be supervised by a university on your part.

What should you bring along?

• Educational Background: Currently pursuing a master's degree in electrical engineering, computer science or a comparable qualification.
• Technical Skills: Knowledge in meta-learning, Bayesian methods, NAS, and network compression. Proficiency in Python, PyTorch, Docker, and Git.
• Practical Experience: Familiarity with deploying deep neural networks on edge hardware.
• Personal Attributes: Highly motivated and eager to collaborate in a team.
• Language Proficiency: Business-fluent English, both written and verbal.

What do we offer?

• Comprehensive mentoring & onboarding.
• Personal & professional development.
• Flexible working hours.
• Digital offers & mobile working.
• Attractive remuneration.
• Apartment offers for students (subject to availability & only Munich).
• And many other benefits - see bmw.jobs/benefits

You are enthused by new technologies and an innovative environment? Apply now!

At the BMW Group, we see diversity and inclusion in all its dimensions as a strength for our teams. Equal opportunities are a particular concern for us, and the equal treatment of applicants and employees is a fundamental principle of our corporate policy. That is why our recruiting decisions are also based on personality, experience and skills.

Find out more about diversity at the BMW Group at bmwgroup.jobs/diversity

Earliest starting date: from 10/01/2024

Duration: 6 months

Working hours: Full-time

Contact:
BMW Group HR Team
+49 89 382-17001