Operations Research Scientist

Howmet Aerospace•Whitehall, MI

21d•Onsite

About The Position

Howmet Aerospace is seeking an exceptional Operations Research Scientist at our Howmet Research Center in Whitehall, MI. This position is part of a multidisciplinary Research & Development team responsible for advancing the state-of-the-art in aerospace manufacturing at our casting, alloy, core and rings manufacturing facilities. This role sits at the intersection of advanced mathematical optimization, digital twin engineering, and AI integration, driving the next generation of intelligent production scheduling and decision support systems across our casting, alloy, core, and rings facilities throughout the world. Role Overview The Operations Research Scientist will design and implement optimization engines and digital twin models with integration of predictive machine learning (ML) components to enable data‑driven, autonomous decision making. The ideal candidate will have a deep expertise in mathematical optimization and digital twin development, strong analytical maturity, and the ability to independently formulate and validate complex models that support Howmet’s facilities.

Requirements

Graduate degree (MS or PhD) with specialization in operations research.
Demonstrated expertise in ILP/MILP modeling, constraint programming, and solver technologies (Gurobi, CPLEX, OR Tools, Pyomo, PuLP).
Working knowledge of machine learning, feature engineering, and model evaluation.
Demonstrated experience in digital twin development and simulation modeling
Employees must be legally authorized to work in the United States. Verification of employment eligibility will be required at the time of hire.
Visa sponsorship is not available for this position.
This position entails access to export controlled items and employment offers are conditioned upon an applicants ability to lawfully obtain access to such items.

Nice To Haves

5+ years of experience in operations research, optimization modeling, or production scheduling.
Hands on experience implementing optimization models in Python, including data preparation, model construction, and solver integration.
Ability to independently design, test, and validate new mathematical formulations.
Experience applying OR techniques to manufacturing, supply chain, or industrial systems.
Experience developing large scale scheduling models (job shop, flow shop, batching, resource constrained scheduling).
Familiarity with stochastic optimization, robust optimization, or reinforcement learning for decision making.
Strong statistical background and experience analyzing industrial/manufacturing data.
Exceptional communication skills and ability to work both independently and in cross functional teams.

Responsibilities

Develop advanced optimization models — Formulate ILP, MILP, MIP, CP, network‑flow, and scheduling models for complex production planning, sequencing, and resource‑allocation problems.
Build and refine production‑scheduling engines — Design constraints, objectives, heuristics, and solver strategies; perform scenario analysis and model validation.
Develop and maintain digital‑twin models — Create simulation‑based and analytical representations of manufacturing systems to support optimization, experimentation, and future agentic‑AI workflows.
Analyze large‑scale manufacturing datasets — Use Python, SQL, and OR toolkits to extract constraints, validate assumptions, quantify system behavior, and identify bottlenecks.
Integrate optimization with ML systems — Collaborate with ML engineers to incorporate cycle‑time models, scrap‑risk models, demand forecasts, and other predictive components into optimization workflows.
Prototype new mathematical formulations — Explore novel modeling approaches to improve throughput, reduce WIP, and optimize resource utilization.
Conduct statistical and multi‑factor analyses — Evaluate system interactions, constraints, and performance drivers using rigorous quantitative methods.
Communicate results effectively — Translate complex optimization and simulation insights into clear recommendations for technical and non‑technical stakeholders.
Collaborate with manufacturing teams — Validate optimization outputs, support plant trials, and integrate solutions into production workflows.
Promote an optimization‑driven culture — Advocate for data‑driven decision‑making and the adoption of advanced OR/AI tools across the organization.