About The Position

As Sweden's national center for applied AI, AI Sweden is looking for a master thesis student to join their NLU team. The project focuses on evaluating synthetic data generation strategies for delta learning, specifically to address the challenge of "translationese" artifacts in machine-translated data used for training Large Language Models (LLMs). The goal is to investigate if delta learning, using Direct Preference Optimization (DPO), can be used to synthesize documents that differ only in fluency, thereby steering models towards better fluency without negatively impacting other capabilities. The project involves a literature study, implementation of controlled DPO training runs, and evaluation using standard benchmarks.

Requirements

  • Ongoing Master’s studies in Computer Science, Data Science, Machine Learning, Engineering Physics, or a related quantitative field.
  • Proficiency in Python and hands-on experience with modern deep learning frameworks (PyTorch, Hugging Face ecosystem).
  • Familiarity with LLM post-training alignment (e.g., SFT, DPO, RLHF/RLVR) or context-extension.
  • Comfort running distributed GPU training in Linux/HPC environments.
  • Curiosity, self-driven, and eager to work at the frontier of open-weight European AI research (LLMs).
  • Ability to design rigorous experiments and let data challenge assumptions.

Responsibilities

  • Conduct a literature study on DPO methodologies, synthetic data generation pipelines, and LLM evaluation benchmarks focusing on translationese artifacts.
  • Implement controlled DPO training runs using Prelude 9B.
  • Compare a baseline before fluency mitigation against runs after fluency mitigation, analyzing the effect of data choices and training hyperparameters.
  • Evaluate fluency, safety, and adequacy using JudgeArena and standard multilingual benchmarks to measure Elo rating improvements.

Benefits

  • Opportunity to work alongside leading AI scientists and change leaders.
  • Engage with research questions that have long shelf-life and are widely applicable to Swedish industry and the public sector.
  • Potential for publications at competitive venues.
  • Experience a culture of research excellence.
  • Work in an organization that combines governmental influence with startup agility.
  • Close contact with government, academia, and private and public sectors.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service