The Job

Master Thesis: ML-Based Analysis of Classical and Quantum Random Number Generators

Technology, Data & Digital · Data, AI & Analytics · Data Science · Machine Learning · Cybersecurity

Join for updates

In short

Ericsson is seeking a master's thesis student to investigate ML-based analysis of classical and quantum random number generators. The thesis involves reviewing ML extensions to randomness tests, implementing Transformer architectures, and evaluating their performance against established methods and quantum data. The goal is to assess if machine learning can detect statistical dependencies or entropy deficiencies not caught by conventional tests.

Responsibilities

  • Conduct a literature review of machine-learning-based extensions and alternatives to established randomness tests.
  • Design, implement, and compare compact Transformer architectures trained from scratch for next-bit and next-block prediction on binary sequences.
  • Evaluate the resulting model-based test using weak pseudorandom number generators, NIST SP 800-90A Deterministic Random Bit Generators (Hash_DRBG, HMAC_DRBG, CTR_DRBG), and data from a Quantum Random Number Generator.
  • Compare model results with established statistical randomness tests.
  • Analyze the relationship between prediction performance, compression-based measures, and min-entropy estimates from NIST SP 800-90B.
  • Interpret differences observed between PRNG and QRNG data.

Requirements

  • Enrolled in the final year of an MSc programme in Physics, Engineering Physics, Computer Science, Electrical Engineering, Applied Mathematics, Cybersecurity, or a closely related field.
  • Strong Python programming skills.
  • Hands-on experience with PyTorch or TensorFlow.
  • Ability to design, implement, train, and evaluate neural-network architectures from scratch.
  • Good understanding of probability, statistics, information theory, and fundamental machine-learning concepts.
  • Familiarity with data preparation, training and validation workflows, performance evaluation, and reproducible experimentation.
  • Understanding of binary data representation and sequential data processing.
  • Proficiency in spoken and written English.
  • Ability to work independently, manage a 20-week research project, document results, and communicate findings clearly through technical reports and presentations.

Desired Qualifications

  • Experience with Transformers, sequence modelling, natural language processing, or time-series analysis is a strong advantage.
  • Familiarity with NumPy, pandas, and scikit-learn, or a demonstrated ability and willingness to learn new tools quickly.
  • Basic knowledge of randomness, entropy estimation, statistical testing, cryptography, or pseudorandom and quantum random-number generation is advantageous.

Benefits

  • Outstanding opportunity to use skills and imagination to push the boundaries of what is possible.
  • Challenge to build solutions never seen before to some of the world's toughest problems.
  • Joining a team of diverse innovators.
  • Encouraging a diverse and inclusive organization is core to our values.
  • Championing diversity and inclusion in everything we do.
  • Belief that collaborating with people with different experiences drives innovation.
  • Encouragement for people from all backgrounds to apply.
  • Opportunity to realize full potential as part of the Ericsson team.
  • Ericsson is proud to be an Equal Opportunity Employer.
#Machine Learning#Random Number Generators#Quantum Computing#Information Security#Deep Learning
Ericsson Logo

Company

Ericsson

Job Posted

1 day ago

Employment Type

Internship

WorkMode

On Site

Experience Level

Entry

Locations

Stockholm, Sweden

Qualification

Master

Applicants

Be an early applicant