Machine Learning Engineer

Compensation: Competitive (TBD)

Security Clearance: Must be eligible to obtain and maintain a U.S. Security Clearance

We are seeking a highly skilled Data Science Engineer to build and support advanced machine learning capabilities for Space Domain Awareness (SDA) analytics systems. This role focuses on developing trajectory classification and anomaly detection models, maintaining scalable analytics pipelines, and creating robust evaluation frameworks for sparse, noisy, and incomplete observational data.

The ideal candidate combines strong machine learning expertise with software engineering discipline and has experience working with time-series, state-estimation, or tracking-related systems. You will collaborate closely with astrodynamics, software, and embedded systems teams to ensure models are both scientifically sound and operationally deployable.

• Develop AI/ML models for trajectory classification across orbital regimes and object families.
• Build anomaly detection models to identify unusual dynamical behavior and emerging patterns.
• Design, integrate, and maintain end-to-end analytical pipelines covering observation processing, orbit estimation, propagation, hypothesis generation, and classification.
• Develop benchmarking and evaluation frameworks to assess model accuracy, convergence behavior, false-positive and false-negative rates, confidence calibration, and performance under degraded observation conditions.
• Design experiments that validate model generalization through held-out datasets, data degradation studies, and independent benchmark comparisons.
• Create calibrated confidence and uncertainty metrics suitable for operational decision-making.
• Partner with embedded systems engineers to optimize model size, memory usage, and inference latency for resource-constrained environments.
• Implement model optimization techniques such as quantization, pruning, and architecture simplification.
• Contribute to systems engineering activities, including data flow design, model lifecycle management, retraining strategies, and technology roadmap planning.
• Maintain a high-quality, reproducible, and well-documented codebase using software engineering best practices.

• Bachelor's or Master's degree in Computer Science, Data Science, Applied Mathematics, Statistics, Aerospace Engineering, Physics, or a related quantitative discipline.
• 4+ years of experience developing and deploying machine learning solutions.
• Strong proficiency in Python and scientific computing libraries such as Num Py, Sci Py, and Pandas.
• Experience with modern deep learning frameworks, preferably PyTorch.
• Proven experience building ML systems for time-series, sequential, tracking, or state-estimation-related data.
• Strong understanding of model evaluation methodologies, including:
• Uncertainty quantification
• Dataset bias and failure analysis
• Experience with version control, testing frameworks, reproducible environments, and software development best practices.
• Excellent technical writing and communication skills.
• Ability to obtain and maintain a U.S. Security Clearance.

• Experience with physics-informed machine learning or hybrid physics/ML approaches.
• Knowledge of orbit determination, object tracking, or multi-target data association methods (e.g., JPDA, MHT).
• Experience deploying machine learning models to embedded or edge computing platforms.
• Familiarity with model compression, quantization, and inference optimization techniques.
• Experience supporting government, defense, aerospace, or advanced R&D programs.
• Understanding of Technology Readiness Levels (TRLs) and product maturation processes.
• Experience developing anomaly detection systems for rare-event or weakly labeled datasets.

• Work on challenging, mission-critical problems in the space and advanced analytics domain.
• Collaborate with exceptional engineers, scientists, and technical experts.
• Develop cutting-edge machine learning solutions with real-world impact.
• Thrive in an innovative, fast-paced, and highly collaborative environment.
• Enjoy competitive compensation, benefits, and long-term growth opportunities.