The driving force behind our success has always been the people of AspenTech. What drives us, is our aspiration, our desire and ambition to keep pushing the envelope, overcoming any hurdle, challenging the status quo to continually find a better way. You will experience these qualities of passion, pride and aspiration in many ways — from a rich set of career development programs to support of community service projects to social events that foster fun and relationship building across our global community.

The Role

AspenTech is seeking a highly motivated PhD intern to join our research and development efforts in the Manufacturing & Supply Chain (MSC) group. This internship focuses on pioneering hybrid machine learning and mathematical optimization approaches to address Crude Scheduling Optimization (CSO) challenges at industrial scale.

This role is ideal for a student passionate about process systems engineering, operations research, optimization algorithms, and AI-driven decision-making. You will work closely with senior researchers and developers to advance a novel framework that blends fast linear programming (LP) approximations with sequential optimization methods such as model predictive control, reinforcement learning, Bayesian optimization, or related techniques.

The intern will have the rare opportunity to contribute to both cutting‑edge research and real-world industrial applications used by global refineries.

Your Impact

• Formulate and analyze optimization models for crude scheduling, including LP-based relaxations and sequential refinement strategies.

• Design and implement optimization and/or machine learning components (e.g., MPC, RL, Bayesian optimization) to explore solution‑improvement workflows.

• Develop prototype computational workflows to evaluate hybrid optimization pipelines.

• Conduct numerical experiments comparing speed, robustness, and accuracy across solution strategies.

• Investigate performance tradeoffs between traditional CSO and hybrid approximate approaches.

• Document research findings, prepare internal reports, and present results to senior technical staff.

• Collaborate with AspenTech researchers, software developers, and domain experts.

What You'll Need

• Current PhD student in: Process Systems Engineering, Operations Research, Industrial Engineering, or a closely related field.

• Strong interest and background in formulating and solving optimal scheduling and/or planning problems.

• Familiarity with sequential optimization approaches, such as: Reinforcement Learning, Model Predictive Control (MPC), Bayesian Optimization.

• Fluency in modeling and solving optimization problems in at least one language/platform, such as: Pyomo, GAMS, JuMP, AMPL, Python, Julia, MATLAB, C++ (optimization focus).

• Preferred additional skills: Experience with bi‑level optimization,

  Understanding of graph theory or network flow optimization,

  Object‑oriented programming experience,

• Familiarity with industrial process models or scheduling workflows.

• Experience with industrial‑scale optimization in a real-world refinery scheduling context.

• Hands-on exposure to machine learning + optimization hybrid algorithms.

• Mentorship from technical leaders in AspenTech’s optimization and scheduling technology teams.

• Opportunity to contribute to potential publications or future product features.

#LI-WJ1