Data Scientist in New York at Jobgether

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Data Scientist based in United States.

This role focuses on solving complex resource allocation challenges through advanced optimization and machine learning. You will design models that help allocate scarce parts and resources across competing programs while balancing operational constraints and business priorities. Working across the full modeling lifecycle, you will move from problem formulation and data exploration to validation and production deployment. The position combines rigorous quantitative analysis with practical collaboration across program and supply-chain stakeholders. You will work with real-world data to develop forecasting capabilities that inform critical allocation decisions. This is an opportunity to apply advanced data science techniques to high-impact problems where model quality, explainability, and business value matter.

• Design and implement optimization models, including mixed-integer linear programming and constraint programming, to allocate scarce parts and resources across competing programs.
• Develop machine learning models that forecast demand, supply risk, and part availability, and integrate those forecasts directly into allocation logic.
• Translate ambiguous and competing program priorities into formal objective functions, constraints, and measurable modeling requirements.
• Validate model outputs against historical allocation decisions and stakeholder expectations, refining formulations as new requirements and constraints emerge.
• Build and maintain data pipelines that keep optimization models current with live inventory, demand, and program data.
• Analyze complex datasets and identify patterns, risks, and opportunities that can improve resource allocation decisions.
• Communicate modeling tradeoffs, assumptions, recommendations, and potential risks to program, supply-chain, and business stakeholders.
• Mentor junior data scientists on optimization techniques, modeling approaches, and quantitative best practices.
• Partner with software engineers to productionize optimization and machine learning models as scalable services.
• Contribute to the continuous improvement of modeling methodologies, data workflows, and decision-support capabilities.

Requirements:

• Master’s or PhD in Operations Research, Applied Mathematics, Computer Science, Industrial Engineering, or a related quantitative discipline, or equivalent practical experience.
• 6+ years of experience developing optimization and/or machine learning models for resource allocation, scheduling, supply chain, or similarly complex decision-making problems.
• Deep hands-on experience with optimization solvers such as Gurobi, CPLEX, or OR-Tools and with formulating MILP and constraint optimization problems.
• Strong Python programming skills, including experience with machine learning frameworks such as scikit-learn or PyTorch and data manipulation libraries such as pandas and NumPy.
• Experience working with messy, complex, real-world supply chain, inventory, or program data.
• Strong quantitative problem-solving skills and the ability to translate ambiguous business requirements into rigorous mathematical models.
• Excellent written and verbal communication skills, with the ability to explain complex technical concepts and modeling tradeoffs to non-technical stakeholders.
• Ability to work effectively in a consultative, customer-focused environment while balancing technical rigor with practical business needs.
• Passion for technology, intellectual curiosity, self-motivation, and a strong commitment to delivering high-quality solutions.
• Preferred: experience solving allocation problems within aerospace, defense, or manufacturing supply chains.
• Preferred: familiarity with ERP systems such as SAP and how allocation decisions influence procurement and production planning.
• Preferred: experience deploying optimization models as production services through APIs or batch pipelines.
• Preferred: exposure to reinforcement learning or Bayesian methods for decision-making under uncertainty.

Benefits:

• Opportunity to work on advanced optimization, machine learning, and decision-support solutions addressing complex real-world resource allocation challenges.
• Exposure to mixed-integer programming, constraint optimization, ML-driven forecasting, and production-scale modeling.
• Collaboration with program, supply-chain, software engineering, and business stakeholders.
• Opportunity to contribute to high-visibility initiatives where analytical recommendations directly support operational decision-making.
• Mentorship opportunities and the ability to contribute to the development of junior data science talent.
• Continuous learning environment focused on emerging AI, machine learning, cloud, and technology practices.
• Inclusive and collaborative culture that encourages technical curiosity, innovation, and knowledge sharing.
• Opportunity to work on solutions spanning optimization, automation, AI/ML, and enterprise technology transformation.
• Confidential handling of candidate information in accordance with applicable EEO guidelines.