You will explore and enhance latent world models for autonomous driving, conducting experiments and collaborating with students and engineers to improve motion planning capabilities.
Anforderungen
- •Enrolled Master student in Computer Science
- •Very good academic performance
- •Good knowledge in (self-)supervised learning
- •Very good knowledge of PyTorch
- •Applied knowledge in Python and C++
- •Structured and independent work
- •Strong communication skills
Deine Aufgaben
- •Research state-of-the-art latent world models.
- •Finetune world models using automotive datasets.
- •Conduct experiments on public and internal datasets.
- •Evaluate world models for motion planning.
- •Collaborate with PhD students and model engineering team.
Deine Vorteile
Remote work options
6-month duration with extension
35-hour work week
Original Beschreibung
# Internship / Master Thesis - Latent Predictive World Models for End-2-End Autonomous Driving (f/m/d)
## YOUR TEAM
We offer you an exciting opportunity for your master thesis or for an internship in our ADAS/AD Pre-Development team in in the field of model engineering for autonomous driving. For the following topic you get the responsibility: latent predictive world models. The aim of this master thesis / the internship is to assess the current research on latent world models, to evaluate how they can be employed and to integrate a pre-trained model in our AD/ADAS stack and/or learning environment. The department works on software and machine learning models for automated driving in urban environments. Within this department, we are a team of ambitious and highly motivated experts in the field of self-driving vehicles working in an agile environment to advance the autonomous driving stack.
## WHAT YOU WILL DO
* Research and assess the state-of-the-art of latent world models for autonomous driving
* Finetune existing world models on automotive datasets for latent state forecasting
* Conduct extensive experiments on public and internal datasets
* Assess the usage of world models for end-2-end motion planning and closed-loop training
* Work closely with our PhD students and the model engineering team
## WHO YOU ARE
* Enrolled Master student in the area of Computer Science, Robotics, Electrical Engineering or similar
* Very good academic performance
* Good general knowledge in the field of (self-)supervised learning, transformer-based architectures, and (vision) foundation models
* Very good knowledge of machine learning frameworks such as PyTorch
* Applied knowledge in software development and programming in Python and C++
* Structured and independent work, above-average commitment and flexibility
* Strong communication skills and analytical understanding
## NICE TO KNOW
* Remote work options within Germany
* Duration: 6 months with the option to extend
* 35-hour week
At CARIAD, we embrace individuality and diversity because we believe our differences make us stronger. We actively seek to build teams with a variety of backgrounds, perspectives, and experiences. Our goal is to create an environment where everyone feels valued and empowered to contribute. If you need assistance with your application due to a disability, please reach out to us at careers@cariad.technology - we are happy to support you.