Hybrid Quantum-Neural Solvers for Mixed-Integer Nonlinear Programming

Master's Thesis
Hybrid Quantum-Neural Solvers for Mixed-Integer Nonlinear Programming
Ref. 2026_021

Mixed-integer nonlinear programming (MINLP) problems are hard in general and remain intractable for state-of-the-art optimization solvers for many real-time applications at operational scale. In this master thesis, the candidate will investigate decomposition-based approaches that separate MINLP into discrete and continuous subproblems, addressing each with the different computational paradigms: quantum optimization for the combinatorial and neural solvers (i.e. AI surrogates) for the continuous part.

Various decomposition strategies will be explored and evaluated with respect to the resulting quantum circuit characteristics (e.g., circuit depth, connectivity, and parameter efficiency) and their suitability for execution on current and future quantum hardware. The proposed concepts will be demonstrated and benchmarked for topology optimization under AC optimal power flow (AC-OPF) constraints for electric grids.

This work aligns closely with IBM Research’s vision for quantum-centric supercomputing, in which quantum computing and classical AI methods are co-designed to address problems beyond the reach of either paradigm alone. The ideal candidate will bring a strong foundation in quantum computing, familiarity with machine learning for optimization, and the motivation to push the algorithmic frontier on industrially relevant hard optimization problems.

Why Join Us?

You will join a world-class research environment and collaborate closely with researchers in quantum computing, AI, and optimization. You will gain access to state-of-the-art quantum hardware and software platforms, advanced AI toolchains, and high-performance computing resources. Our environment encourages innovation and supports scientific publications and intellectual property creation.

Preferred Qualifications

Bachelor’s degree in computer science, electrical engineering, physics, mathematics, or a related field
Background in one or more of the following domains: quantum information theory, quantum algorithms, (combinatorial) optimization, machine learning/AI, or computational physics
Strong programming skills in Python; experience with scientific computing and deep learning on compute clusters
Experience with quantum software frameworks (e.g., Qiskit) is a plus
Self-motivated, team-oriented, and eager to work on interdisciplinary research problems

Diversity & Work Environment
IBM is committed to fostering diversity and inclusion in the workplace. You will join an open, multicultural research environment that values different perspectives and supports flexible working arrangements. Our goal is to help all genders and backgrounds thrive professionally while maintaining a healthy work–life balance.

How to Apply

If you are interested in this position, please submit your application through the link below.

Apply