AI Engineer - Allocation and Packing Systems

Gallatin AI, Inc.; El Segundo (CA); On-site; USD 100,000 - 130,000; Full time

Job summary

A logistics technology firm based in California seeks an AI Engineer to own allocation and packing models that enhance resupply systems. The role involves designing and implementing efficient packing solutions while addressing real-world constraints. Applicants should possess strong programming skills in Python and a solid foundation in operations research and optimization techniques. The position offers the opportunity to work on complex logistics challenges that have real-world impact.

Qualifications

• Experience translating allocation logic into deterministic, testable production code.
• Experience with bin packing, knapsack, or multidimensional packing problems.
• Strong foundation in applied algorithms for physical feasibility problems.

Responsibilities

• Design and implement packing and allocation models.
• Integrate packing outputs into resupply and routing workflows.
• Manage data inputs required for allocation and packing.

Skills

Strong programming skills in Python

Operations research

Optimization

Applied algorithms for resource allocation

Ability to reason about physical constraints

Education

Background in operations research, applied math, industrial engineering

Tools

Linear programming

Mixed-integer programming

Job description

Overview

AI Engineer – Allocation & Packing Systems

About The Role: We’re looking for an AI Engineer to own allocation and packing models for Gallatin’s resupply systems. This role builds the decision systems that safely translate AI and agent reasoning into executable logistics plans. This role focuses on determining whether supplies can be physically assigned and fit within available assets under real-world constraints.

You will work closely with feasibility, routing, and AI engineers to ensure packing solutions are realistic, efficient, and executable at scale.

Responsibilities

• Design and implement packing and allocation models for transport assets.
• Encode constraints related to volume, weight, compatibility, sequencing, and asset usage.
• Balance packing efficiency with runtime and operational realism.

• Implement and tune heuristics or exact approaches for packing and allocation problems.
• Scale packing solutions across large fleets and dynamic inputs.
• Evaluate tradeoffs between optimality, speed, and explainability.

• Own data inputs required for allocation and packing, including asset and supply properties.
• Validate, normalize, and maintain packing-related datasets.
• Manage edge cases and incomplete data directly.

• Integrate packing outputs into resupply and routing workflows.
• Partner with teams to validate physical executability.
• Validate solutions through scenario testing and operational feedback.
• Ensure AI-generated plans cannot bypass physical feasibility or constraint enforcement layers.

Core Skills

• Strong programming skills in Python or similar, with experience translating allocation logic into deterministic, testable production code.
• Strong foundation in operations research, optimization, or applied algorithms for resource allocation and physical feasibility problems.

Or Background

• Background in operations research, applied math, industrial engineering, or related fields.
• Familiarity implementing allocation and assignment algorithms, including matching, prioritization, and constraint-based allocation under competing demands.
• Experience modeling and solving packing problems, such as bin packing, knapsack, or multidimensional (2D/3D) packing problems.
• Experience encoding capacity, compatibility, priority, and physical constraints in allocation and packing systems.
• Familiarity with optimization techniques such as linear programming, mixed-integer programming, or heuristic and approximation methods for NP-hard problems.
• Experience balancing solution quality, feasibility, and computational performance in large-scale or time-sensitive systems.
• Experience with vehicle loading or palletization problems.

Systems Thinking

• Ability to reason about physical constraints and edge cases.
• Comfort owning data pipelines and assumptions end-to-end.
• Strong attention to correctness and failure modes.

Bonus Points

• Experience integrating packing with simulation systems.
• Prior exposure to defense or government planning environments.
• Experience with Machine Learning models, experimentation (e.g., A/B testing) and causal inference.