Senior AI/ML Engineer

This is a fully remote position, open to applicants in Virginia.

📋 Description

• Design, develop, and validate machine learning models focused on RF emitter identification, which includes feature engineering from sensor data, creating training pipelines, evaluating models, and refining them based on results.

• Perform hands-on exploratory data analysis on RF sensor datasets using Python and Jupyter notebooks, which involves writing and executing analytical code, characterizing feature distributions, identifying data quality issues, and documenting findings.

• Implement and manage ML data pipelines, which includes ingesting NDF sensor streams, applying rollup and preprocessing logic, creating training datasets, and ensuring pipeline accuracy on constrained edge hardware without cloud reliance.

• Collaborate with the technical lead and Principal AI/ML Engineer to examine RF sensor data quality, attribution reliability, and feature behavior under contention by writing code to characterize error sources, validate assumptions, and reproduce findings.

• Generate clear technical documentation for experiments, model configurations, and results, ensuring reproducibility through disciplined versioning, and contributing to monthly status reports and team knowledge sharing.

⛳️ Requirements

• Over 5 years of practical experience in machine learning, data science, or RF signal processing.

• Proven expertise in Python for machine learning and data science tasks, including PyTorch or TensorFlow for model development, Pandas/NumPy for data manipulation, and scikit-learn or similar tools for evaluation and baseline modeling.

• Hands-on experience in designing, training, and assessing deep learning models, particularly in metric learning, Siamese networks, or other similarity-learning architectures, on real-world, noisy, and imbalanced datasets.

• Practical experience in addressing real-world data quality issues, such as missing values, label noise, class imbalance, systematic bias, and sensor artifacts, with the ability to diagnose and resolve these issues without discarding valid data.

• Capability to develop and execute ML pipelines on Linux-based systems without relying on cloud infrastructure or GPU acceleration, optimizing for CPU-only inference and multi-threaded data processing on resource-limited x86 hardware.

• Knowledge of RF signal characteristics, passive receiver phenomenology, and interpretation of sensor data, including understanding processing artifacts, attribution ambiguities, and measurement limits typical in signals intelligence datasets.

• Direct experience applying machine learning, particularly in metric learning, deep learning networks, or similarity-learning architectures, to RF or time-series signal data, encompassing feature engineering, training pipeline development, and model validation.

• Familiarity with TDMA network protocols or military datalink systems, and a keen interest in understanding the signal processing challenges present in dense, contested electromagnetic environments.

• Understanding of direction-finding, time-difference-of-arrival (TDOA), or related passive geolocation concepts, with a focus on their mathematical foundations and common failure modes over operational experience.

• Experience with binary serialization formats (FlatBuffers, Protocol Buffers) and high-throughput sensor data pipelines that operate in near-real-time on resource-constrained hardware.

• Relevant certifications in machine learning, data science, or related technical fields (e.g., TensorFlow Developer Certificate; PyTorch Certified Associate; AWS Certified Machine Learning — Specialty; Microsoft Certified: Azure AI Engineer Associate; Certified Analytics Professional (CAP); etc.).

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Comprehensive health, dental, and vision insurance plans.

• Opportunities for professional development and continuous learning.

• Flexible work schedule and remote work options.

• Collaborative and innovative work environment.