PhD Position in Distributed Edge AI for Autonomous Drone Inspection
36 months (30 hours per week) | Planned start in January 2027
The Research Division Distributed Systems, E194-02, Institute of Information Systems Engineering, TU Wien, is offering a position (30 hours/week) as a pre-doc project assistant for 36 months. The estimated starting date is January 1, 2027. Entry-level salary as a pre-doc project researcher is covered by the Austrian Collective Agreement for university staff and is €2.832,08 per month gross, 14x per year.
The Project
Bridge infrastructure inspections generate large volumes of imagery, and drones have limited onboard compute, battery capacity, and connectivity. The EdgeAI-Drone (Intent-Driven Edge-AI Drone Inspection for Bridge Infrastructure), funded by the Austrian Research Promotion Agency (FFG), uses inspection goals to guide image analysis and reporting during missions. In collaboration with academic and industrial partners, it will optimize inference with large language models (LLMs) and vision-language models (VLMs) on embedded devices and study where to run them as conditions change. The aim is timely, accurate inspection results within energy and bandwidth limits.
Your Tasks
- Profile and optimize LLM and VLM inference on embedded devices using optimization methods.
- Design policies that decide at runtime which model to use, where to run it, and what resources to allocate across the drone, edge servers, and cloud.
- Integrate the inference components with mission and reporting software developed by the project partners.
- Design reproducible experiments to measure performance, energy, and quality metrics.
- Publish your results at international research venues and complete a doctoral thesis at TU Wien.
Required Qualifications
- A master’s degree or equivalent in computer science, informatics, business informatics, computer engineering, robotics, or a related field by the start of employment.
- Very good knowledge of machine learning demonstrated by your Master’s thesis, projects, or publications
- Strong foundations in distributed systems or edge and cloud computing, including how compute and network constraints affect workload placement.
- Hands-on experience training, developing, deploying, or evaluating deep learning or computer vision models with PyTorch or a comparable framework.
- Strong programming skills in Python, Java, or C++ and experience building and testing prototypes on Linux.
- Very good written and spoken English.
Desirable Qualifications
- Experience optimizing LLM or VLM inference through quantization, hardware acceleration, or model partitioning.
- Experience deploying or profiling AI models on edge devices or embedded platforms.
- Experience with workload offloading, resource-aware scheduling, or datasets from drone inspections.
- Publications or experience in national or international research cooperation.
What We Offer
- A creative environment in one of the most livable cities in the world.
- A young and international team of researchers.
- A range of attractive social benefits (see Benefits).
- A work environment that is well equipped with the newest hardware and software technology.
- Continuing personal and professional education.
- A vibrant consortium spanning universities, research organizations, and industry.
- A high-impact research topic with real-world validation in industrial production.
- The possibility to present your research results at international top conferences.
Application Information
Please prepare one PDF containing a brief research statement, CV, a brief explanation of your thesis, degree certificates, and academic transcripts. If it is available, include your master’s thesis or a link if available, along with any relevant publications or code. To ask a question or express interest, contact Dr. Reza Farahani, the project coordinator, at r.farahani@dsg.tuwien.ac.at.
Application deadline: December 2, 2026
Candidates are not eligible for a refund of expenses for travelling and lodging related to the application process.