PhD Student in AI and Digital Twins for Resilient Energy Systems

AI is developing fast - far beyond the speed of traditional technological evolution, and energy systems are becoming ever more complex, distributed and interconnected. Do you, just like us, want to help build the intelligent, data-driven tools that will keep tomorrow's energy systems reliable and resilient?

We are looking for a motivated PhD student who wants to develop AI methods and digital twins for resilient energy systems, with a focus on district heating and cooling and building energy systems. You will combine machine learning, modelling and simulation to better understand, predict and strengthen these systems under uncertainty and disturbance - working at the intersection of AI, digital twins and the built environment.

About us

At RISE, the unit Connected Intelligence conducts applied research and development at the meeting point between artificial intelligence, connected systems and the physical world. We build intelligent, data-driven solutions that turn sensor data, models and real-time information into decisions - for industry, public agencies and society.

Our team is interdisciplinary and hands-on. We are a group of researchers who develop practical, trustworthy AI solutions together with industry partners, public agencies and academia. As a PhD student you will be employed at RISE and enrolled as a doctoral student at KTH Royal Institute of Technology, with an academic supervisor at KTH in addition to your supervisors at RISE.

About the role

In this position you will pursue doctoral research on AI and digital twins for resilient energy systems, with a focus on district heating and cooling networks and building energy systems. The overall direction is set, while the specific scientific contributions will be shaped together with you. You will:

Develop AI and machine-learning methods for modelling, monitoring and forecasting in district heating and cooling networks and building energy systems

Build and validate digital twins that mirror the behaviour of these energy systems and their assets in real time

Investigate how data-driven methods can improve the resilience and efficiency of district heating/cooling and building energy systems against faults, disturbances and changing conditions

Combine physics-based models with data-driven approaches (e.g. hybrid and physics-informed machine learning)

Validate methods on real data and in relevant testbed or simulation environments together with energy utilities, property owners and research partners

Publish your results in leading international conferences and journals, and present them in research and industry forums

Contribute to research and innovation projects within the unit

The position is a full-time, time-limited doctoral employment, normally up to five years including approximately 20% departmental work, leading to a PhD. The role is based in Kista, Stockholm, and you are expected to spend 3 days per week in KTH, Campus Valhallavägen for coursework, research collaboration, and possibly teaching duties.

Because some projects may be security-sensitive, a security clearance may be required now or in the future.

Who are you?

Required qualifications:

A Master's degree (or equivalent) in computer science, electrical or energy engineering, applied mathematics, physics or a closely related field

Solid foundation in machine learning and/or modelling and simulation

Good programming skills (e.g. Python)

A strong interest in energy systems - especially district heating/cooling and building energy systems - and in digital twins

Ability to work independently as well as in a team

Excellent communication skills in English, written and spoken

Meriting qualifications:

Experience with deep learning and modern AI frameworks (e.g. PyTorch, TensorFlow)

Strong knowledge of energy systems, especially district heating/cooling and building energy systems, combined with strong modelling and simulation skills

Experience with digital twins, simulation or physics-informed/hybrid modelling

Experience working with time-series data, sensor data or real-time systems

Experience with optimisation, control or uncertainty quantification

Prior research experience or scientific publications

Good communication skills in Swedish

Personal qualities:

A strong technical interest and a desire to work at the forefront of technology

Curiosity and a drive to learn, explore and solve complex problems

Strong analytical skills

Communicative and able to collaborate with both technical and non-technical stakeholders

Proactive, with the ability to take initiative and see the bigger picture in complex systems

Are we a good match?

We work across the entire AI pipeline - from data collection and communication to modelling, learning and decision-making - with a focus on trustworthiness, robustness and real-world impact. Resilient and efficient district heating/cooling and building energy systems are a strategic societal challenge for the energy transition, and digital twins powered by AI are one of the most promising tools to address it.

As a PhD student at RISE you will have:

The opportunity to do impactful research on a strategically important societal challenge

Access to real data, testbeds and simulation environments together with leading partners

Close collaboration with experienced researchers and industry partners

A combination of applied research and academic training, leading to a PhD

A flexible, supportive and research-driven work environment