PhD Researcher

Operations Research & Machine Learning

I'm Juan Pablo Morande, a PhD candidate in Industrial and Systems Engineering at Auburn University. I work on logistics, scheduling, and forecasting problems using optimization and machine learning.

View Projects Contact Me Resume ↓
Focus Areas
Optimization Simulation Logistics Scheduling Explainable AI Multi-Agent LLM Systems
Expected Graduation

PhD, Auburn University, December 2026 (expected)

Looking For

Applied Research Engineer roles in the US. Open for relocation. Available for immediate start.

Work Authorization
Currently F-1 Visa STEM OPT Eligible H-1B1 Eligible (Chile FTA, lottery-exempt)
01

About Me

I'm a fifth-year PhD candidate in Industrial and Systems Engineering at Auburn University. My research covers operations research, machine learning, optimization, and simulation, with a dissertation on integrating prediction and optimization for complex logistics problems. I've been on the INFORMS student chapter board every year since 2022, including a term as President in 2024–25 and currently serving as the E-council representative.

My projects have included two-dimensional truck loading optimization, military aircraft and crew scheduling for U.S. Air Force wargaming simulations, deep learning applied to illicit supply chain detection, freight rate forecasting with explainable AI, and drone-based order-picking in warehouses. In 2024, I spent a semester as a visiting researcher at NTNU in Norway, developing closed-loop supply chain models. More recently, I've been working on LLM-based systems, focused on a multi-agent framework for automated algorithm design, alongside projects in fine-tuned RAG legal advising and agent-based economic simulation.

I'm originally from Chile and fluent in both Spanish and English. I got into research through humanitarian logistics simulation at Universidad de los Andes, and I'm now looking for an Applied Research Engineer role where I can put optimization, data science, and ML to work on real problems.

0 Years of
Research
0 Conference
Presentations
0 Journal
Manuscripts
0 Years on Local
INFORMS Board
02

Experience

2021 — Present

Research & Teaching Assistant

Auburn University

  • Developed optimization models and heuristics for aircraft and crew allocation and scheduling to support U.S. Air Force wargaming and strategic planning (WASP project, AFMC through Frontier Technology Inc., 2023–2025).
  • Researched deep learning and reinforcement learning applications in illicit supply chains, focusing on opioid precursor trafficking patterns (DHS CAOE Grant through Arizona State University, 2024–2025).
  • Designed hierarchical optimization methods for a two-dimensional vehicle loading problem with heterogeneous fleets, minimizing delays in an industrial case study with a Colombian motorcycle assembler. Manuscript under review at European Journal of Operational Research.
  • Applied explainable AI methods over LSTM, Transformer, and TFT architectures to forecast freight rate dynamics in Chilean ports, using LIME and SHAP to surface the main drivers behind rate changes. Manuscript under review at Annals of Operations Research.
  • Led applied projects spanning a discrete-event simulation for a Chilean mining operation, a hybrid RAG system over legal documents for a Chilean law firm, and LLM-based agentic simulations.
  • TA for Engineering Economics, Statistical Quality Control, Data Mining, and Adaptive Optimization.
Feb — May 2024

Visiting Researcher

Norwegian University of Science and Technology (NTNU)

  • Developed closed-loop supply chain MILP models for strategic and product design decisions, evaluated through scenario-based analysis under disruption.
  • Published in Omega (2025): Stochastic programming framework for supply chain viability.
Oct 2020 — Jul 2021

Research Assistant

Universidad de los Andes, Chile

  • Implemented metaheuristic optimization (Simulated Annealing, Tabu Search, Genetic Algorithms) coupled with discrete-event simulation for humanitarian logistics in natural disaster scenarios.
  • Extended the methodology from my undergraduate thesis, which benchmarked these metaheuristics against variance reduction techniques (Common Random Numbers, Antithetic Variables, Dynamic Replications) on DES models.
  • Work culminated in a conference presentation at ICPR Americas 2020.
Dec 2019 — Feb 2020

Software Development Intern

Snow Consulting

  • Supported the development area with data analysis and Business Intelligence applications.
  • Explored and implemented data mining techniques, with hands-on work on data cleaning and balancing imbalanced datasets.
Dec 2018 — Aug 2019

Teaching & Research Assistant

Universidad de los Andes, Chile

  • Taught weekly review sessions for the Statistical Methods course.
  • Co-authored a Spanish-language teaching guide and user manual for SIMIO simulation software, tailored to an undergraduate simulation course.

Education

PhD Industrial & Systems Engineering Auburn University 2021 — December 2026 (expected) Dissertation: Integrating Prediction and Optimization: Data-Driven Methods for Complex Logistics Problems (advisors: Alice Smith, Daniel Silva).
MS Industrial & Systems Engineering Auburn University 2023
BS Industrial Engineering, Minor in Political Science Universidad de los Andes, Chile 2012 — 2020 Thesis: Benchmarking statistical techniques and metaheuristic optimization for discrete-event simulation (advisor: Sergio Quijada).

Awards & Leadership

INFORMS AU Student Chapter Leadership Secretary (2022–23), VP (2023–24), President (2024–25), VP (2025–26), E-council Representative (2026–Present). Magna Cum Laude Chapter Award (2025) 2022 — Present
Amazon SCOT INFORMS Scholarship Scholarship to attend the 2022 INFORMS Annual Meeting 2022
SPEC Cybersecurity Summer Program Hands-on cybersecurity program at UVA at Wise, Virginia 2019
Founder Political Student Organization Universidad de los Andes, Chile 2014 — 2016
03

Featured Projects

Research

01

Freight Rate Forecasting with XAI

Forecasted shipping freight rates in Chilean ports using Temporal Fusion Transformers, LSTMs, and attention-based architectures, with LIME and SHAP for interpretability and Bayesian methods for hyperparameter tuning. The explainability analysis surfaced the main drivers behind rate changes for maritime logistics stakeholders.

PyTorchTransformersLIMESHAPTime Series
02

Multi-Objective Flight Scheduling

Developed optimization models and heuristics for U.S. Air Force wargaming simulations, scheduling military aircraft and crews across missions subject to range, refueling, and personnel constraints. The solution approach combines MILP formulations with metaheuristic solvers, including Simulated Annealing, Tabu Search, and Genetic Algorithms.

PyomoGenetic AlgorithmsMILPMulti-Objective
03

Closed-Loop Supply Chain Optimization

Developed a stochastic programming framework that integrates product development and design decisions into supply chains facing disruptive events, informed by two Norwegian circular manufacturing case studies. Results showed resilience improvements of 4–5%, budget savings of 2–10%, and measurable gains in sustainability and circularity. Published in Omega (2025); developed during a research visit at NTNU in Norway.

Stochastic ProgrammingMILPSupply Chain
Read Paper →
04

Two-Dimensional Truck Loading Optimization

Developed a three-stage matheuristic combining MILP models to solve a two-dimensional vehicle loading problem faced by a Colombian motorcycle assembler operating a heterogeneous fleet. The approach maximizes on-time deliveries, minimizes the number of trucks used, and reduces unloading rehandles during delivery stops. Across 300 test instances, the matheuristic improved the company-defined performance metric by an average of 27% over one-dimensional baselines and saved 2.69 trucks per day on average, particularly under relaxed credit constraints. Implemented in Java with CPLEX.

MILPMatheuristicTwo-Dimensional Bin PackingLogistics
05

Drone Order-Picking Optimization

Modeled cooperative order picking by drones and workers in warehouses, starting from independent routing and building up to fully coordinated systems with synchronization, battery constraints, and multi-trip drone scheduling. Formulated the problem as a CVRP with MTZ subtour elimination and Big-M linearizations, minimizing makespan across multiple scenarios.

MILPCVRPDronesWarehousing
06

Memory-Enhanced Multi-Agent Framework for Combinatorial Optimization

A memory-enhanced agentic system that generates Python heuristics for combinatorial optimization problems in parallel through coordinator, coding, and observer agents. The core contribution is a multi-perspective knowledge synthesis layer: five analyst LLMs, each drawing on a distinct philosophy-of-science tradition (Popperian falsification, Inductivist generalization, and three others), distill each iteration's results into evolving knowledge documents stored as episodic memory, which the coordinator reads before steering the next round of assignments. Benchmarked on Job-Shop Scheduling (OR-Library instances), single-machine tardiness, and MAX-SAT.

LLMMulti-AgentEpisodic MemoryJob-Shop SchedulingPydanticAI
07

Mining Robotics Simulation

Built a discrete-event simulation model for a mining company evaluating proposed changes to the robots that lay out detonation grids at active sites. The model simulated grid fulfillment under different robot configurations, comparing alternatives on completion time and throughput to support the company's assessment of upgrade options.

SIMIODiscrete-Event SimulationRoboticsMiningThroughput Analysis
08

Decision-Focused Learning for Berth Allocation

Third dissertation chapter: trains an LSTM forecaster of vessel arrival and service times jointly with a MILP berth allocation model using decision-focused learning (SPO+ loss and perturbation-based gradients) so that the predictor minimizes schedule cost regret instead of forecast error. Evaluated against a standard predict-then-optimize baseline on Port of San Antonio (Chile) historical data, with SHAP and LIME comparing feature attributions before and after DFL training.

Decision-Focused LearningSPO+MILPLSTMBerth AllocationGurobi
09

Illicit Supply Chain Detection with Deep Learning

Research on deep learning and reinforcement learning methods for detecting patterns in illicit supply chains, with a focus on opioid precursor trafficking. Funded by the U.S. Department of Homeland Security Center for Accelerating Operational Efficiency (CAOE) in partnership with Arizona State University (2024–2025).

Deep LearningReinforcement LearningSupply Chain SecurityPattern DetectionDHS CAOE

Applied Projects

10

Web Development & Showcase Sites

Built a range of portfolio and business websites, including bilingual company pages, personal sites, and this portfolio itself, each with responsive layouts and clean visual design.

HTML/CSSJavaScriptNext.jsResponsive Design
11

Health & Fitness Mobile App

Cross-platform mobile application for health and fitness tracking across iOS, Android, and the web, featuring nutrition logging, weight tracking, and progress dashboards. Started as an excuse to try AI-powered development tools (and to avoid paying for fitness apps).

React NativeSQLiteiOSAndroid
12

Chilean Pension Fund Legal Advisor

A compliance advisor deployed at a Chilean pension fund administrator (AFP) to assist legal teams with financial regulations. It pairs a hybrid RAG pipeline (bi-encoder retrieval plus cross-encoder reranking over more than 4,500 legal document chunks) and multi-hop agents with a QLoRA fine-tuned Qwen2.5-7B model that answers regulatory questions and cites the source documentation.

LLMHybrid RAGQLoRACross-Encoder Reranker
13

Emergent Small Town Economy with LLM Agents

A simulation in which LLM agents autonomously run the economy of a small town: they work, start businesses, set their own prices, socialize, and reflect at the end of each day. Business types, products, and custom actions are generated dynamically by the model, with dedicated judge agents validating the plausibility of new businesses and actions before they enter the world. Runs locally on vLLM with Qwen2.5-3B-Instruct.

Agent-Based SimulationEmergent EconomyLLM JudgesLoRARLHF
04

Skills & Expertise

Optimization & OR

  • Mathematical Optimization (MILP, Stochastic, Robust)
  • Heuristics, Metaheuristics & Matheuristics
  • Scheduling & Routing Problems
  • Simulation (DES, ABM) with Variance Reduction (CRN, Antithetic Variables)
  • Experimental Design (DOE) & Statistical Methods

Machine Learning

  • Time-Series Forecasting (LSTM, Transformers, TFT)
  • Reinforcement Learning (Q-Learning, DQN, PPO)
  • Explainable AI (LIME, SHAP)
  • Bayesian Modeling (Hierarchical, MCMC)
  • Decision-Focused Learning

LLMs & Agentic Systems

  • Hybrid RAG (Bi-Encoder + Cross-Encoder Reranking)
  • Multi-Agent Coordination
  • Long-Term Memory Architectures
  • Fine-Tuning (SFT, QLoRA, RLHF)
  • Agentic LLM Workflows
  • Hugging Face, Ollama, vLLM, PydanticAI

Programming & Tools

  • Python (primary), R, Java, SQL
  • PyTorch, NumPy, Pandas, scikit-learn
  • Pyomo, Gurobi, CPLEX
  • SIMIO, Arena, Plant Simulation, SimPy
  • Git & Version Control
05

Publications

2025
Published

Supply chain viability by integrating R-imperatives, product development, and design decisions: A stochastic programming framework

Omega, Journal of Management Science

doi.org/10.1016/j.omega.2025.103317 →

Two additional manuscripts are under review: a freight rate forecasting study with explainable AI (Annals of Operations Research) and a two-dimensional truck loading paper (European Journal of Operational Research).

Conference Presentations

INFORMS Annual Meeting Atlanta, GA • Phoenix, AZ • Indianapolis, IN 2025 • 2023 • 2022
IFORS 23rd Triennial Conference Santiago, Chile 2023
OPTIMA XV Chilean Conference on OR Coquimbo, Chile 2025
ICPR ICPR Americas 2020 Virtual 2020
06

Contact

Happy to hear from you about job opportunities, research collaborations, or just to connect on LinkedIn.

Send me an Email Connect on LinkedIn Download Resume
Email jpm0112@auburn.edu LinkedIn linkedin.com/in/jpmorande GitHub github.com/jpm0112 Google Scholar View Publications