AIOps empowered by Knowledge Graphs Full-time

Offer Description

There are many organizations today that use complex software systems to support their business operations. Modern systems involve a large number of integrated services that run across several backends connected via multiple layers of middleware. When an incident occurs, the complexity of the systems often makes it difficult to find the root cause quickly without proper knowledge, tailored methods or tools. There are two important aspects of the problem that we will explore in our research. First, it is the background knowledge about the architecture, such as systems, their services, components, and integration patterns, processing models, configurations to throttle inbound or outbound requests, or capacity constraints to control resources available to running processes. And second, it is the massive amounts of operations data both structured and unstructured that the systems and its components produce in every moment. A meaningful combination of the two, supported by strong methods to analyse the knowledge and learn from the data, will lead to better results of root cause analysis and troubleshooting tasks and will improve the architectures resilience.

The major goal of our research is to develop novel methods that will utilize core concepts from the Semantic Web community around Knowledge Graphs and data analysis backed up by machine learning algorithms. That said, the research will target the Services and Semantic Web communities. The two communities actively work to improve a variety of machine learning methods to solve various types of problems including the ones mentioned herein. For example, deep learning research is concentrated around neural network models known as Long-Short Term Memory to detect and predict anomalies in operations data and that use an internal state that represents contextual information. We will build on the latest research results and further explore the use of neural networks such as Self-Organizing Map that can be used to reduce dimensions of large datasets and further perform clustering analysis to detect types of events or errors in time. There are results in the area of AIOps that use deep learning to detect anomalies in unstructured logs but they still lack abilities to work with the dynamic nature of log streams that may change over time. In this respect, we will explore how the neural network model can be dynamically adapted to a continuously growing dataset produced by a log stream such as applying aging to data and decreasing old data significance. On the other hand, Knowledge Graphs are an important source of background knowledge for explainability and interpretability of a deep learning system. Our research will use Knowledge Graphs as a background knowledge of a service architecture to discover links in data and learn, for example, patterns of incidents. The following are few overlapping examples of works that our research will cover: Analysis of large streams of semi-structured data in the context of the service architecture, Discovery of links in large datasets and correlate data to detect anomalies in systems’ behaviour, Learning patterns of incidents from historical data to detect an incident before it happens, Error types detection from semi-structured error logs to optimize error correction processes.

Where to apply
E-mail
[Please click the Apply button for the link or address]

Requirements

Research Field Computer science ” Computer systems Education Level PhD or equivalent

Skills/Qualifications

Education, research experience and publication record in areas relevant to the research topic

Specific Requirements

Required documents to be uploaded to the Application form webpage

1. CV including a list of
   a) Invited presentations to conferences and/or international advanced schools,
   b) Organisation of International conferences (membership in the steering and/or programme committee),
   c) Prizes, Awards, and Scholarships
   d) Projects funded and/or active participation,
   e) Examples of participation in industrial innovation, if any.
2. List of publications
   Journal papers first, conference papers second, followed by patents.
3. Research proposal
   Select one of the topics offered
   Describe the scope, objectives and foreseen research and training activities, including cooperation with the Associated partner.
   Required sections: 1) Excellence, 2) Impact incl. expected outputs of the project, 3) Quality and Efficiency of the Implementation 4), Personal motivation: description of career goals, foreseen advancement in research and professional skills of the Applicant.
   Consult your proposal with the respective Mentor. You are encouraged to communicate with the mentor before you submit the application.
4. PhD diploma (or certificate of defense)

Languages ENGLISH Level Good

Additional Information

Benefits

Gross monthly salary of 83 531 CzK/month*
Family allowance 9044 CZK/month (for applicants with dependent family members)
Travel support for conferences and secondments
Research costs1

*The gross monthly salary CZK is under the standard scheme in the Czech Republic and includes mandatory social and health insurance. Therefore, the gross salary contains an employee contribution to social and health insurance of 11% and it is standardly taxable (15 % rate). Some tax discounts are given to e.g. employees with children.

Example: a single researcher would get 61 813 CzK as net salary

The offered salary is equivalent to the standard MSCA individual postdoc award, and it is highly competitive (double the average salary in Czechia, the typical salary of an Associate professor)

Eligibility criteria

Experience :
* PhD degree at the time of beginning of the contract
Applicants who are close to the defense of their doctoral thesis will also be considered eligible to apply

* maximum of 8 years experience in research , from the date of the award of their PhD degree till the time of the Call opening (July 26, 2025) . Years of experience outside research and career breaks will not count towards the above maximum.

* previous studies compatible with the project they intend to apply with

Mobility : applicants must not have resided or carried out their main activity in the Czech Republic for more than 12 months in the 3 years prior to the Calls’ deadline (career breaks not counted).

Selection process

2-stage

Applicants should select one topic from the List of topics and prepare their own Research proposal.
It is recommended that the applicants contact the Mentor of the relevant topic and consult their proposal in advance.

The Application form is open for modifications until the deadline.

Website for additional job details

https://vitvar.com

Work Location(s)

Number of offers available 1 Company/Institute Department of Software Engineering Country Czech Republic City Prague 6 Postal Code 160 00 Street Thákurova 9 Geofield