Master Thesis - Edge AI for Real-Time Scenario Detection in Autonomous Driving (m/f/d)
Master Thesis - Edge AI for Real-Time Scenario Detection in Autonomous Driving (m/f/d)
Ingolstadt, DE, 85053
Master Thesis - Edge AI for Real-Time Scenario Detection in Autonomous Driving (m/f/d)
We are CARIAD, the automotive software company of the Volkswagen Group. Our teams build automotive software platforms and digital customer functions for iconic brands like Audi, Volkswagen, and Porsche – supporting the Volkswagen Group in becoming the leading automotive technology company. With CARIDIANS in Germany, the USA, China, Estonia, and India, we are transforming automotive mobility for everyone.
Join us and be part of this exciting journey!
YOUR TEAM
The Data Selection and Scenario Mining department develops cutting-edge methods to accelerate the training of best-in-class Automated Driving and Advanced Driver Assistance Systems (ADAS). We focus on identifying the most valuable data from millions of driving hours to train our neural networks efficiently. You will be embedded in an agile team of Computer Vision experts, ML Engineers, and Backend Developers, working closely with our Active Learning specialists to solve real-world perception challenges.
WHAT YOU WILL DO
- Real-Time Enabler: Enable the vehicle to autonomously identify rare driving scenarios by prototyping "online" unsupervised learning models (e.g. Deep Isolation Forests) capable of running in real-time.
- Offline-to-Online Migration: Port and adapt existing offline Python methodologies into efficient, modern C++ implementations suitable for embedded in-vehicle use.
- Legacy Adaptation: Revitalize algorithms from previous project generations by adapting them to work with current sensor stacks and modern perception outputs.
- Benchmarking: Conduct a comparative study between "heavy" offline models and your "lightweight" online implementations to quantify the trade-offs between accuracy and computational cost.
WHO YOU ARE
- Enrolled student in Computer Science, Robotics, Software Engineering, Physics, Mathematics, or a comparable field
- Programming: C++ skills are required. Proficient knowledge of Python is required to understand and migrate existing research prototypes
- Machine Learning: Basic understanding of ML concepts (unsupervised learning, anomaly detection) is required
- "Engineer at heart" who enjoys looking under the hood and solving low-level integration challenges, rather than just training models in a notebook
- Fluent in English; good knowledge of German is beneficial
- Structured, independent, and capable of working in an agile team environment
NICE TO KNOW
- Remote work options within Germany
- Duration: 3 - 6 months
- 35 hours/week
- Salary: 13,90€/hour
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.
We are CARIAD, the automotive software company of the Volkswagen Group. Our teams build automotive software platforms and digital customer functions for iconic brands like Audi, Volkswagen, and Porsche – supporting the Volkswagen Group in becoming the leading automotive technology company. With CARIDIANS in Germany, the USA, China, Estonia, and India, we are transforming automotive mobility for everyone.
Join us and be part of this exciting journey!
YOUR TEAM
The Data Selection and Scenario Mining department develops cutting-edge methods to accelerate the training of best-in-class Automated Driving and Advanced Driver Assistance Systems (ADAS). We focus on identifying the most valuable data from millions of driving hours to train our neural networks efficiently. You will be embedded in an agile team of Computer Vision experts, ML Engineers, and Backend Developers, working closely with our Active Learning specialists to solve real-world perception challenges.
WHAT YOU WILL DO
- Real-Time Enabler: Enable the vehicle to autonomously identify rare driving scenarios by prototyping "online" unsupervised learning models (e.g. Deep Isolation Forests) capable of running in real-time.
- Offline-to-Online Migration: Port and adapt existing offline Python methodologies into efficient, modern C++ implementations suitable for embedded in-vehicle use.
- Legacy Adaptation: Revitalize algorithms from previous project generations by adapting them to work with current sensor stacks and modern perception outputs.
- Benchmarking: Conduct a comparative study between "heavy" offline models and your "lightweight" online implementations to quantify the trade-offs between accuracy and computational cost.
WHO YOU ARE
- Enrolled student in Computer Science, Robotics, Software Engineering, Physics, Mathematics, or a comparable field
- Programming: C++ skills are required. Proficient knowledge of Python is required to understand and migrate existing research prototypes
- Machine Learning: Basic understanding of ML concepts (unsupervised learning, anomaly detection) is required
- "Engineer at heart" who enjoys looking under the hood and solving low-level integration challenges, rather than just training models in a notebook
- Fluent in English; good knowledge of German is beneficial
- Structured, independent, and capable of working in an agile team environment
NICE TO KNOW
- Remote work options within Germany
- Duration: 3 - 6 months
- 35 hours/week
- Salary: 13,90€/hour
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.
Ingolstadt, DE, 85053