Data Science Engineer

Our client is an innovative and mission-focused organization seeking an experienced, driven Data Science Engineer. In this role, you will develop the machine-learning components and integration infrastructure that support the company’s space domain awareness (SDA) analytics pipelines. Across various programs, you will build trajectory-classification and anomaly-detection models that operate on orbit-determination output. You will also build and maintain the benchmarking and evaluation frameworks necessary to ensure these pipelines perform accurately under sparse, gapped, and noisy observation conditions.

A strong emphasis is placed on characteristics that determine real-world operational value: managing false-positive behavior under degraded observations, calibrating confidence metrics suitable for operator use, and ensuring inference costs remain compatible with constrained onboard processing. You will work closely with astrodynamics and embedded-systems teams to ensure that models reflect genuine dynamical structures and can be successfully deployed within strict onboard resource limits., Develop AI/ML models for trajectory classification across various orbit regimes and families, and for the detection of anomalous dynamical behavior.

Integrate and maintain end-to-end analytical pipelines spanning observation processing, hypothesis generation, orbit estimation, propagation, and classification.

Define system interfaces and take full ownership of a shared, reproducible codebase.

Build benchmarking and evaluation frameworks to measure estimator convergence behavior, classification accuracy and confusion structure, false-positive/negative characterization, time-to-custody, and sensitivity to track gaps and elevated measurement uncertainty.

Design experiments that distinguish genuine model generalization from dataset artifacts-including held-out families, degraded-observation ablations, and cross-checks against independent reference datasets.

Produce calibrated confidence metrics suitable for downstream operational use, documented precisely enough to support critical operator decisions.

Partner with embedded-systems staff to characterize model complexity, memory footprint, and inference latency; identify quantization, pruning, or architectural simplifications that meet deployment constraints.

Contribute machine-learning expertise to CONOPS and systems-engineering activities, including data-flow definition, model lifecycle and retraining considerations, and the identification of critical technology elements.

BS or MS in Computer Science, Applied Mathematics, Statistics, Aerospace Engineering, Physics, or a related quantitative field.

4+ years of applied machine learning experience (or equivalent).

Strong proficiency in Python and the scientific stack (NumPy, SciPy, pandas).

Fluency in at least one deep-learning framework (PyTorch is strongly preferred).

Demonstrated experience building ML systems on time-series, sequential, or state-estimation-adjacent data, rather than just tabular or vision benchmarks.

Sound understanding of evaluation methodology, including class imbalance, calibration, uncertainty quantification, and the failure modes of small or synthetically generated datasets.

Strong software-engineering discipline sufficient for a shared codebase, including version control, testing, reproducible environments, and documented interfaces.

Clear technical writing skills for producing high-quality customer-facing deliverables.

Must be able to obtain and hold a U.S. security clearance.

Preferred Qualifications

Experience with physics-informed ML or hybrid approaches that embed dynamical structure into learned models.

Familiarity with orbit determination, tracking, or multi-target data association (e.g., JPDA, MHT, or similar).

Prior experience with model compression, quantization, or deployment to constrained and embedded targets.

Prior work on government R&D programs (SBIR/STTR, AFRL, DARPA, Space Force) and familiarity with Technology Readiness Level (TRL) terminology.

Experience with anomaly detection in environments where anomalies are rare, poorly labeled, or defined purely by a physical model.

Impact: Be part of a collaborative, innovative, and mission-focused environment where your ideas and skills have a significant, real-world impact.

Growth: Help shape the company culture, set the foundation for future success, and build world-class teams.

Compensation: Enjoy a competitive salary, comprehensive benefits, and an attractive equity package.