Job DescriptionWhat you bring (please specify briefly but as detailed as possible)Currently enrolled in Computer Science, Mathematics, Physics, or Operations ResearchStrong programming skills in Python and working knowledge of at least one optimization framework (Gurobi, CPLEX, Xpress, or OR-Tools) — requiredSolid foundations in at least one of: mathematical optimization (LP/MIP, heuristics, metaheuristics), machine learning, or algorithm designAbility to design and run reproducible experiments, analyse results rigorously, and document findings clearlyInterest in applied, enterprise-scale problems — not purely academic settingsNice to have: experience with GPU programming (CUDA, cuOpt), ML frameworks (PyTorch, scikit-learn), C++, or operations research decomposition techniques.What you'll buildYou will work on the algorithmic core of the SCM Optimization Service — the mathematical engine behind SAP's supply chain planning. The focus is on three areas:Classical Optimization. You will develop and improve algorithms for core supply chain and logistics problems. The work covers mathematical programming (MIP), heuristics, and metaheuristics, applied to real-world planning scenarios at enterprise scale.AI-Enhanced Optimization. You will develop and evaluate machine learning techniques that augment classical optimization: learned heuristics and prediction models for planning parameters. The goal is to improve planning quality and responsiveness beyond what classical solvers alone can achieve.GPU-Accelerated Solvers. The unit is evaluating GPU architectures for large-scale combinatorial optimization. You will prototype and benchmark solver approaches on GPU hardware, assess which problem classes benefit from massive parallelism (e.g. large-scale supply planning, production scheduling), and contribute to the unit's evaluation of various frameworks.Where you belongYou will join a technically focused team that develops the optimization capabilities for SAP's supply chain applications. The work is research-adjacent but product-oriented: your findings feed directly into the unit's algorithm portfolio, deployed across SAP Integrated Business Planning, SAP Transportation Management, and SAP Logistics Management.The team operates at the intersection of mathematical optimization, AI, and quantum computing. Work location is Walldorf, 20 hours per week with flexible scheduling.Your set of application documents should contain a cover letter, a resume in table form, school leaving certificates, certificate of enrollment, current university transcript of records, copies of any academic degrees already earned, and if available, references from former employers (including internships). Please also describe your experience and skills in foreign languages and computer programs / programming languages.

Job DescriptionWhat you bring (please specify briefly but as detailed as possible)Currently enrolled in Computer Science, Mathematics, Physics, or Operations ResearchStrong programming skills in Python and working knowledge of at least one optimization framework (Gurobi, CPLEX, Xpress, or OR-Tools) requiredSolid foundations in at least one of: mathematical optimization (LP/MIP, heuristics, metaheuristics), machine learning, or algorithm designAbility to design and run reproducible experiments, analyse results rigorously, and document findings clearlyInterest in applied, enterprise-scale problems not purely academic settingsNice to have: experience with GPU programming (CUDA, cuOpt), ML frameworks (PyTorch, scikit-learn), C++, or operations research decomposition techniques.What you'll buildYou will work on the algorithmic core of the SCM Optimization Service the mathematical engine behind SAP's supply chain planning. The focus is on three areas:Classical Optimization. You will develop and improve algorithms for core supply chain and logistics problems. The work covers mathematical programming (MIP), heuristics, and metaheuristics, applied to real-world planning scenarios at enterprise scale.AI-Enhanced Optimization. You will develop and evaluate machine learning techniques that augment classical optimization: learned heuristics and prediction models for planning parameters. The goal is to improve planning quality and responsiveness beyond what classical solvers alone can achieve.GPU-Accelerated Solvers. The unit is evaluating GPU architectures for large-scale combinatorial optimization. You will prototype and benchmark solver approaches on GPU hardware, assess which problem classes benefit from massive parallelism (e.g. large-scale supply planning, production scheduling), and contribute to the unit's evaluation of various frameworks.Where you belongYou will join a technically focused team that develops the optimization capabilities for SAP's supply chain applications. The work is research-adjacent but product-oriented: your findings feed directly into the unit's algorithm portfolio, deployed across SAP Integrated Business Planning, SAP Transportation Management, and SAP Logistics Management.The team operates at the intersection of mathematical optimization, AI, and quantum computing. Work location is Walldorf, 20 hours per week with flexible scheduling.Your set of application documents should contain a cover letter, a resume in table form, school leaving certificates, certificate of enrollment, current university transcript of records, copies of any academic degrees already earned, and if available, references from former employers (including internships). Please also describe your experience and skills in foreign languages and computer programs / programming languages.