Master Thesis Projects in Sensing

This year, we're trying something a little different to make it easier for you to explore and apply for our master thesis projects. Instead of separate ads for every topic, we've grouped all projects into three main clusters — each focused on a different part of autonomous driving. You're welcome to apply to one, two, or all three clusters if you like, but later in the application process, we'll ask you to prioritize the projects you're most excited about, in each cluster.

Help Cars See, Understand, and React to the World

In autonomous driving, everything starts with perception. How a vehicle senses, interprets, and understands its surroundings determines how safely and intelligently it can act. In this master thesis cluster, you'll work on projects that push the boundaries of how cars perceive the world — turning raw sensor data into actionable awareness that powers real-world decision-making.

From transforming sensor data into meaningful insights with cutting-edge AI, to developing systems that detect drivable areas and predict how environments will change, your work will directly shape how vehicles see, understand, and interact with the world around them.

Sensing & Perception: Thesis Projects (Cluster A)
Here Are The Master Thesis Projects Offered In This Cluster — Each Topic Below Is a Separate Project You Can Apply For

• Project 1: Captioning Engine for AD/ADAS data using Multi-Modal Large Language Models – Use advanced LLMs to describe and interpret sensor data from autonomous vehicles.
• Project 2: World Model Online Evaluation – Develop methods to continuously evaluate how vehicles represent and understand their environment.
• Project 3: Realistic Radar Simulation Using Transfer Learning for Autonomous Driving – Build radar simulations that improve perception model training and validation.
• Project 4: Self-Supervised Representation Learning on LiDAR Point Clouds – Enable vehicles to learn meaningful features from raw LiDAR data without manual labeling.
• Project 5 (in Lund, where you need to be located): Free-Space Network Heads for Drivable Area Estimation – Improve how cars detect drivable areas and plan safe navigation.
• Project 6 (in Lund, where you need to be located): Explicit Model Pre-Training for 3D Occupancy Prediction – Develop foundational models that enhance 3D environmental understanding.
• Project 7: Deep-Learning-Based Headlight Beam Control – Explore how perception and deep learning can adaptively control headlights for safer driving.

Depending on which project you're offered, you'll conduct applied research in areas such as
AI, sensor fusion, and 3D perception
. You'll design and train deep learning models using real or simulated sensor data and explore innovative ways to process inputs from LiDAR, radar, and cameras. Throughout the projects, you'll collaborate closely with experienced researchers and engineers — and the results of your work will directly contribute to the future of safer, smarter autonomous vehicles.

We Offer Several Master Thesis Projects Across Three Clusters

• Sensing & Perception (this one) – how the car sees and understands the world
• AI Tooling & Infrastructure – the data, platforms, and tools that power autonomous systems
• Planning, Decision-Making & Safety – how the car predicts, plans, and acts intelligently

Each cluster has its own job ad and a detailed project PDF with background on all topics. You'll receive the PDF in a
separate email after you apply
to help you explore the projects in more depth and choose the ones that best match your skills and interests.

So Who Are We Looking For?
We're seeking passionate and curious
Master's students
from (including but not limited to):

• Computer Science / Software Engineering
• Machine Learning / Artificial Intelligence
• Robotics / Autonomous Systems
• Signal Processing / Computer Vision

Because this cluster spans several projects, the required skills vary. When you apply, please list
all relevant skills, tools, and knowledge areas
— and describe your
level of experience
with each (e.g., basic, intermediate, advanced). This helps us understand your profile and match you with the project that best fits your background.

Expected Skills & Experience
Typical skills we look for (you're
not
expected to have all):

• Programming (e.g., Python, C++)
• Experience with machine learning or deep learning frameworks (e.g., PyTorch, TensorFlow)
• Understanding of sensor data processing, 3D perception, or sensor fusion
• Knowledge of computer vision, LiDAR/Radar data, or scene understanding
• Familiarity with self-supervised learning, data pipelines, or simulation tools

What's in It for You?

• Work on impactful projects that directly contribute to autonomous driving systems
• Gain hands-on experience with real-world data and cutting-edge technology
• Learn from industry experts and grow your professional network
• Be part of an inclusive and innovative team shaping the future of mobility

How to Apply?
Submit your
CV
,
motivation letter
, and
grade transcripts
.

• Applying as a pair? Include your partner's name in the application.
• Planned start: January 2026 (flexible)
• Application deadline: October 31, 2025 (applications reviewed continuously)

For more information, contact:
Gabriel Campos, Research Manager
–

This role may involve access to sensitive information, trade secrets, and confidential data. Selected candidates may undergo a background check as part of the recruitment process.

More About Zenseact

Our Software Makes a Difference
We use AI-driven technology to fight traffic accidents and make roads safer. Every year, 1.4 million people lose their lives in traffic — we're here to change that.

One Purpose, One Product
We design the complete software stack for autonomous driving and advanced driver-assistance systems. With continuous updates, cars become safer over time — bringing us closer
Towards Zero. Faster.

Culture with People at Heart
We can only succeed together. Our culture is built on care, trust, and belonging — a place where everyone can grow, be themselves, and do their best, both at work and in life.

Zenseact works proactively to create a culture of diversity and inclusion, where individual differences are appreciated and respected. To drive innovation, we see diversity as an asset — we value and respect differences in gender, race, ethnicity, religion or belief, disability, sexual orientation, age, and more.

Interviews are held on a continuous basis, so we highly recommend that you submit your application as early as possible.

One purpose, one product
We are a software company focused on transforming car safety. By developing a complete software stack for autonomous driving and advanced driver-assistance systems, we aim to eliminate car accidents and make roads safer for all. Founded by Volvo Cars, Zenseact operates globally, with teams in Gothenburg and Lund, Sweden; and Munich, Germany.