Wiss. Mitarbeiter_in/Doktorand_in (w/m/d) in Decentralized Accelerators for Efficient Stream Processing

Darmstadt University of Technology
February 17, 2023
Offerd Salary:Negotiation
Working address:N/A
Contract Type:Other
Working Time:Part time
Working type:N/A
Ref info:N/A

At the Distributed and Networked Systems (part of Systems@TUDa) at the Computer Science Department of TU Darmstadt we are looking for a

Research Assistant/PhD Student (all genders)

The starting date is flexible but preferably before April 2023 and the position is initially limited to three years.

Many recent and emerging applications rely on the ability to process data captured on a variety of devices, and these applications often involve data that is generated and consumed outside of the Cloud, by Internet of Things connected devices, sensors, and infrastructure. Data movement to compute resources in the Cloud is inefficient and entails long and unpredictable latencies. Hence, it is important to develop new approaches that offer the benefits of compute offloading while being more inherently decentralized to address the processing of data streams between sensors and the Cloud.

The project you would be joining proposes a new paradigm for computing between sensors and the Cloud through the use of energy-efficient accelerators that dramatically reduce the computing footprint, while also improving latency and scalability for connected applications. Focusing on processing event-driven data streams, we adapt ideas from the increasingly popular serverless computing paradigm, that maps well to distributed computing resources, and exploit FPGAs that have proven capabilities in compute acceleration, to enable efficient, low-latency computing on demand to support emerging applications typical of future cities. Through a novel approach of managing these accelerators as distributed computing resources, we enable efficient on-demand compute offloading. This brings the performance and efficiency benefits of accelerators, that are typically in the Cloud, to existing and emerging decentralized applications.

Qualification Requirements

The following qualifications are required:

  • The candidate must have an MSc in Computer Science, Electric Engineering or an equivalent field (or be in the last semester of MSc studies an complete these before the start date)
  • The candidate must have prior experience with programming distributed systems
  • Prior experience with specialized hardware accelerators (ideally FPGAs) is a plus
  • Industry experience (internships, placements, employment) in relevant topics is a plus.
  • Opportunity for further qualification (doctoral dissertation) is given. The fulfillment of the duties likewise enables the scientific qualifications of the candidate.

    The Technische Universität Darmstadt intends to increase the number of female employees and encourages female candidates to apply. In case of equal qualifications applicants with a degree of disability of at least 50 or equal will be given preference. Wages and salaries are according to the collective agreements on salary scales, which apply to the Technische Universität Darmstadt (TV-TU Darmstadt). Part-time employment is generally possible.

    The application must be in English and must include a Letter of Motivation, which provides evidence of independent thinking, novelty and originality, Documentation of academic degree(s); grade transcripts that document outstanding academic achievement, Curriculum Vitae, which must include two professional/academic references (letters of recommendation will be requested, if needed, directly from the references); Applications may also include a relevant scientific publication written by the applicant and/or the applicant's master thesis Applications without the above-mentioned documents will not be assessed.

    Please send inquiries and applications (referencing the code no.) to Prof. Zsolt István (Zsolt.istvan@cs.tudarmstadt.de).

    By submitting your application, you agree that your data may be stored and processed for the purpose of filling the vacancy. You can find our privacy policy on our webpage.

    Code No. 13

    Published on

    January 06, 2023

    Application deadline

    February 17, 2023

    From this employer

    Recent blogs

    Recent news