MBRDNA is looking to explore and advance Vision-Language Models (VLMs) in the autonomous driving domain to enhance scene understanding, semantic reasoning, visual question answering, and multi-modal intent prediction, ultimately influencing perception and planning pipelines.
Requirements
- Demonstrated experience in developing and training deep learning models, particularly in areas involving multi-modal inputs such as images, video, and text.
- Solid understanding of state-of-the-art vision and language models (e.g., CLIP, BLIP, VLM adaptations of ViT, LLM-integrated frameworks).
- Strong programming skills in Python and familiarity with deep learning libraries (e.g., PyTorch, TensorFlow).
- Currently pursuing or recently graduated from a PhD program in Computer Science, Electrical Engineering, Robotics, or a closely related discipline.
- Publication record in reputable AI/ML/CV/NLP conferences or journals.
- Experience with Autonomous Driving algorithms and systems.
Responsibilities
- Investigate and apply advanced Vision-Language Modeling techniques to autonomous driving challenges, including large-scale transformer-based architectures and multi-modal pre-training.
- Develop and refine vision-language models for tasks such as: Captioning and summarizing complex driving scenes.
- Develop and refine vision-language models for tasks such as: Visual question answering about objects, actions, and intentions in traffic scenarios.
- Develop and refine vision-language models for tasks such as: Aligning textual navigation instructions with visual perception for route planning.
- Collaborate with other team members to integrate novel VLM-based solutions into existing autonomous driving frameworks.
- Evaluate and benchmark model performance on internal and public datasets, identifying gaps and proposing improvements.
- Document findings through internal research reports and contribute to publications in top-tier conferences if suitable results are achieved.
Other
- MS degree in Major in Computer Science, Electrical Engineering, Robotics, or a related field, with a strong focus on machine learning, computer vision, and/or natural language processing etc.)
- 5+ years of relevant work experience.
- Why should you apply?Here at MBRDNA, you create digital ecosystems around cars, you design a language between humans and machines, you make a car even more intelligent - you make the new reality for cars.
- MBRDNA was honored as one of the "Best Places to Work" by BuiltIn in January 2024, a testament to our commitment to creating an exceptional work environment.
- At each of our offices, we foster a culture of collaboration and continuous learning, ensuring every team member can thrive and innovate.
