20 nov
|
Barcelona Supercomputing Center
|
Barcelona
20 nov
Barcelona Supercomputing Center
Barcelona
Position: Post-training Specialist (RE3)
The Barcelona Supercomputing Center - Centro Nacional de Supercomputación (BSC-CNS) is the leading supercomputing center in Spain. The mission of BSC is to research, develop and manage information technologies in order to facilitate scientific progress. BSC combines HPC service provision and R&D; into both computer and computational science (life, earth and engineering sciences) under one roof, and currently has over 1000 staff from 60 countries.
BSC-CNS YouTube Channel
We are particularly interested for this role in the strengths and lived experiences of women and underrepresented groups to help us avoid perpetuating biases and oversights in science and IT research. It has been entrusted by the Spanish and the Catalan governments with the mission to develop fundamental open‑source resources and technologies for Spanish and Catalan. In connection with this, the Area is currently in charge of two flagship projects at the national and regional level: the ALIA project, funded by the Spanish Secretariat of Digitalization and Artificial Intelligence, and the AINA project, aimed at developing AI resources for Catalan, funded by the Catalan Digitalization Department. In addition, it takes part in various EU funded international projects. The Methods and Algorithms for Post-training (MAP) team is looking for engineers with a strong background in Large Language Models, Natural Language Processing and Deep Learning, supported by solid foundations in mathematics and statistics.
Execute and monitor post-training experiments including Instruction Tuning and state-of-the-art Reinforcement Learning techniques (DPO, GRPO and variants and OPD) specifically for Iberian languages.
Implement and scale training workflows using frameworks such as Slime, TRL,
and NeMo-RL to ensure efficient model adaptation.
Develop and curate high-quality datasets in Spanish and other co‑official languages including Catalan, Basque and Galician.
Perform rigorous evaluation of model performance across regional linguistic nuances to ensure high-quality generation and reasoning.
Support the integration of linguistic specificities into the group’s general‑purpose models by collaborating with the senior engineering team.
Bachelor’s degree in Computer Science, Mathematics, Statistics, Engineering or related field.
Master’s degree in Artificial Intelligence, Machine Learning, Computer Science, Data Science, Applied Mathematics or a closely related field.
Solid experience in Fine‑tuning and Post‑training of Large Language Models.
Proficiency in Python and Deep Learning frameworks such as PyTorch.
Hands‑on experience with modern post‑training frameworks like Slime, Verl or NeMo‑RL.
Excellent level of English (written and spoken).
Knowledge of linguistic features and datasets for Spanish and the co‑official languages of Spain.
Fluency in Spanish is highly valued.
Knowledge of Catalan, Basque or Galician is a significant plus.
Strong analytical skills for identifying linguistic biases or performance gaps in regional languages.
Detail‑oriented mindset for data quality and model evaluation.
We offer a full‑time contract (35h/week),
a good working environment, a highly stimulating environment with state‑of‑the‑art infrastructure, versátil working hours, extensive training plan, restaurant tickets, private health insurance, support to the relocation procedures
Duration: Open-ended contract due to technical and scientific activities linked to the project and budget duration
Holidays: 22 days of holidays + 6 personal days + 24th and 31st of December per our collective agreement
Development of the recruitment process
The recruitment process consists of two phases:
Evaluation of previous experience and/or scientific history, degree, training, and other professional information relevant to the position. - The highest‑rated candidates at the curriculum level will be invited to the interview phase, conducted by the corresponding department and Human Resources. The recruitment panel will be composed of at least three people, ensuring at least 25% representation of women.
In accordance with OTM‑R principles, a gender‑balanced recruitment panel is formed for each vacancy at the beginning of the process. After reviewing the content of the applications, the panel will begin the interviews, with at least one technical and one administrative interview. At BSC, we seek continuous improvement in our recruitment processes. For any suggestions or comments/complaints about our recruitment processes, please contact
BSC‑CNS is committed to the principles of the Code of Conduct for the Recruitment of Researchers of the European Commission and the Open, Transparent and Merit‑based Recruitment principles (OTM‑R). This is applied for any potential candidate in all our processes, for example by creating gend
📌 Training Officer (Barcelona)
🏢 Barcelona Supercomputing Center
📍 Barcelona