Job Reference
605_24_CASE_WP_RE1
Position
Research Engineer - ML-Aided Mathematical Optimization (MAMO) - (RE1)
Closing Date
Monday, 30 September, 2024
About BSC
The Barcelona Supercomputing Center - Centro Nacional de Supercomputación (BSC-CNS) is the leading supercomputing center in Spain. It houses MareNostrum, one of the most powerful supercomputers in Europe, and is now hosting entity for EuroHPC JU. The mission of BSC is to research, develop and manage information technologies to facilitate scientific progress. BSC promotes Equity, Diversity and Inclusion, fostering an environment where everyone is appreciated for who they are, regardless of differences.
Context And Mission
Mathematical optimization problems are convex problems solved by discrete optimization, where the objective is the optimal allocation of given resources. The student intern will focus on reducing the computational cost incurred when resolving pure binary integer linear programming (ILP) problems.
Key Duties
Become familiar with concepts: NLP, semantic similarity, ILP formulation, and establish a baseline workflow with Python.
Explore parallelization of the ILP algorithm using the task-based programming model COMP Superscalar ported to Python (PyCOMPSs).
Design a Machine Learning method to reduce the set of feasible solutions for the semantic pairing ILP problem.
Learn a generalizable model to infer reduced sets of feasible solutions for unseen textual summaries.
Relax the pure binary integer constraint on decision variables and inspect obtained semantic similarity solutions.
Prepare a final report detailing methodologies, developed code, and prospective ideas for RL algorithms.
Code developed will be stored in the BSC version-control project repository.
Requirements
Education: Course subjects concentration in mathematics and computer science.
Essential Knowledge and Professional Experience:
Experience in computer science, mathematical analysis, and optimization schemes.
Collaborative and version-controlled work environments (e.g., gitlab, github).
Proficiency in Python 3, C/C++, Unix/Linux.
Understanding of differential calculus, vector analysis, combinatorial optimization.
Additional Knowledge:
Fluent in English.
Knowledge of distributed computing and parallelization paradigms.
Competences:
Good communication and presentation skills.
Ability to work independently and within a team.
Conditions
Full-time contract (37.5h/week).
Duration: Temporary.
23 paid vacation days plus additional holidays.
Competitive salary based on qualifications and experience.
Starting date: 16/09/2024.
Applications procedure and process
All applications must be made through the BSC website and include:
A full CV in English including contact details.
A Cover Letter with a statement of interest in English.
Deadline
The vacancy will remain open until a suitable candidate has been hired.
OTM-R principles for selection processes
BSC-CNS is committed to the principles of equal opportunity and diversity.
#J-18808-Ljbffr