Kungliga Tekniska högskolan, KTH Informations- och kommunikationsteknik

KTH Royal Institute of Technology in Stockholm is the largest and oldest technical university in Sweden. No less than one-third of Swedens technical research and engineering education capacity at university level is provided by KTH. Education and research spans from natural sciences to all branches of engineering and includes Architecture, Industrial Management and Urban Planning. There are a total of 13,400 first and second level students and almost 1,900 doctoral students. KTH has 4,900 employees.

KTH Informations- och kommunikationsteknik bedriver internationellt framstående forskning och utbildning inom materialfysik, fotonik/optik, elektroniksystem, integrerade komponenter och kretsar samt kommunikationssystem. Vår forskning omfattar både grundläggande och tillämpade projekt samt innehåller betydande inslag av innovativ och entreprenöriell verksamhet. Vårt utbildningsutbud är brett och omfattar kandidat- högskoleingenjörs- och civilingenjörsprogram, masterutbildningar samt doktorsprogram. Skolan har ett nära samarbete med svensk och internationell industri, forskningsinstitut samt intresseorganisationer som Kista Science City.

Job description

The department of Electronic and Embedded Systems within KTH Information and Communication Technology is looking for a Postdoc in the area of Brain like intelligence for the Embedded Systems. The complexity of interaction of embedded systems with the environment is increasing because of the need to cope with unpredictable situations. Dealing with this increased complexity using the traditional Von Neumann computing architecture is not scaling well. In contrast, brain-like computing architectures with their ability to continuously learn and adapt, scale much better. While the brains amazing learning capability and computational efficiency has been the envy of the computer architecture community, three factors have prevented brain-like computing becoming main stream solution: lack of sufficient understanding of how brain works, Von Neumann architectures are poorly matched with the requirements and paradigm of brain-like computing and the semiconductor technology to implement the known brain models were not efficient enough. The above factors are reflected in the fact that even super computers consuming Mega Watts of power are not able to simulate an abstract human scale model of cortex in biological real time.

To enable deployment of brain-like intelligence for embedded systems requires bringing together a broad spectrum of disciplines from brain modelling, sensor fusion, autonomous systems, embedded systems and software, custom VLSI design to semiconductor technology. The objective of this position would be to build on existing research activities in these disciplines at KTH to implement a computing engine that corresponds to a small mammalian brain in a size and power consumption level that is suitable for embedded systems. This requires a radical rethink in computing architecture and customization for brain models to fully exploit the inherent embarrassingly parallel nature of such computation. Additionally, it would require exploiting emerging non-volatile memory and 3D integration technologies. Carrying out such a concerted and co-ordinated multi-disciplinary research would be the mandate of this position.

The candidate is also expected to contribute to teaching at up to 20% of their time. This work will be done in close collaboration with Professor Anders Lansners group www.nada.kth.se ala/ and Professor Danica Kragics group (http://www.csc.kth.se/ danik/). This position will be placed in Professor Ahmed Hemanis group (http://web.it.kth.se/ hemani/).

Qualifications

A PhD degree in the area of VLSI design and architecture and some background in brain models, neural networks, machine learning. The candidate is expected to be highly skilled in digital design using HDL, verification, synthesis targeting both ASICs and FPGAs. The position also requires a strong background in mathematics to be able to understand and implement algorithms in signal processing, neural networks, brain models etc. A strong publication record and demonstrated ability to conduct collaborative cross disciplinary research. Excellent command in English both oral and written is a must.

Trade union representatives

You'll find contact information to trade union representatives at KTH:s web page .

Application

The application should include the following documents:

• Full curriculum vitae
• Publication record (pinpoint the most important papers and describe your contributions)
• Motivation letter describing your experience and professional interests
• Degree certificates and transcripts from university and graduate studies
• Two reference letters, which should contain the contact information of the referee (email and phone number)

Log into KTH's recruitment system in order to apply to this position. You are the main responsible to ensure that your application is complete according to the ad. Your complete application must be received at KTH no later than the last day of application.

Others

Form of the employment: Time limited, one year contract with a possibility of extension with one more year

We firmly decline all contact with staffing and recruitment agencies and job ad salespersons.

Type of employment: Temporary position longer than 6 months
Working hours: Full time
Salary: According to agreement and to the general level for postdoc salary
City: Kista
Reference number: I-2015-0021
Published: 2015-01-21
Last application date: 2015-02-28

Please state in the application that you applied via Universitypositions.eu