Fleet Scheduler Data Scientist

Location: Lanham, Maryland, United States

Department: AIT Management

Position Overview

We are seeking a Fleet Scheduler Data Scientist to define, build, and operationalize algorithms that optimize and control this network. This role will lead the design and deployment of AI and ML powered large-scale combinatorial optimization algorithms that drive predictive planning and reactive real-time control loops. This role requires a deep understanding of state-of-the-art techniques in combinatorial optimization of heterogeneous graphs for system scheduling, and must develop an understanding of a host of underlying systems and subsystems to efficiently incorporate their features into both predictive and reactive action planning loops. This person will work in coordination with software engineers to implement the algorithms and models that are developed, and will also work closely with aerospace, network, and operations engineering teams to translate physics- and constraint-driven system behavior into scalable prediction, optimization, and control architectures. 

Key Responsibilities:

• Own the architecture of AI and ML powered satellite and ground scheduling algorithms.
• Design and deploy large-scale combinatorial optimization algorithms, with approaches ranging from mixed-integer programming and heuristics to reinforcement-learning-based solvers operating on heterogeneous graphs.
• Incorporate state-of-the-art techniques in combinatorial optimization, learning-augmented planning, graph-based scheduling, and computational efficiency.
• Create a multi-tiered scheduling system, from high-level control of major satellite activities through mid-level control of system configurations and settings.
• Develop physics-informed ML models that accurately predict satellite behaviors, utilizing simulated spacecraft model data and satellite telemetry data for fine-tuning.
• Ensure all models and optimizers are production-grade: data pipelines, training, validation, deployment, monitoring, and drift management.
• Partner with satellite engineers to develop simulated training data, define key system physics, and ensure models reflect true system behavior and constraints.
• Coordinate with satellite engineers to incorporate fleet modeling into design analysis and trades.
• Identify and drive new opportunities for AI and ML across design, manufacturing, and in-orbit operations. 

Qualifications 

Education:

BS/MS/PhD in Computer Science, Electrical Engineering, Applied Math, Physics, Aerospace, or a related field, or equivalent experience.

Experience:

• 5-7+ years delivering AI, ML, and other optimization systems in production environments.
• Demonstrated experience solving large-scale combinatorial optimization problems (e.g., scheduling, resource allocation, logistics, network capacity).
• Strong background in traditional optimization methods, including mixed-integer programming, constraint programming, or related techniques.
• Experience modeling and solving large-scale problems represented as graphs or heterogeneous graph structures.
• Strong Python and ML/optimization tooling (e.g., PyTorch).
• Experience building data pipelines and deploying models into operational systems. 

Preferred Qualifications:

• Experience with reinforcement learning, multi-agent systems, or hybrid ML + optimization.
• Familiarity with satellite operations and RF communications.
• Experience building real-time or safety-critical decision systems.
• Prior technical leadership of AI/ML or optimization teams. 

Soft Skills:

• Strong cross-functional collaboration skills, partnering effectively with software, aerospace, network, and operations engineering teams.
• Strong communication skills, with the ability to translate complex physics- and constraint-driven system behavior into clear technical requirements.
• Strong analytical and problem-solving skills, with the ability to identify and drive new AI/ML opportunities across design, manufacturing, and operations.
• Meticulous attention to detail in model validation, production readiness, and drift monitoring. 

Technology Stack:

• Python and ML/optimization tooling such as PyTorch.
• Mixed-integer programming, constraint programming, and heuristic optimization solvers.
• Reinforcement learning frameworks and graph-based/heterogeneous graph modeling tools.
• Data pipeline and MLOps tooling for training, validation, deployment, monitoring, and drift management.
• Simulated spacecraft modeling and satellite telemetry data platforms. 

Physical Requirements 

• Ability to lift up to 25 lbs.
• Ability to use a computer for extended periods.
• Ability to work in a standard office environment.
• Ability to travel occasionally to support cross-team collaboration or reviews as needed.

This job description may not be inclusive to the duties and responsibilities listed. Additional tasks may be assigned to the employee from time to time or the scope of the job may change as needed by business demands.