AI/ML Engineer, Senior

Clearance Level: Public Trust US Citizenship: Required Job Classification: Full Time Location: Remote Years of Experience: 5–7 years of relevant experience Education Level: BS or MS in Electrical Engineering, Computer Science, Applied Mathematics, or a closely related quantitative field. Experience may be considered in place of education requirement. Briefly Describe the Work: GITI is seeking a Senior AI/ML Engineer to support an R&D program focused on passive RF emitter identification and network analysis from real-time sensor data streams. The Senior AI/ML Engineer designs, builds, and validates machine learning models for RF emitter identification, conducts hands-on exploratory data analysis on NDF (Network Description File) sensor datasets, and implements ML data pipelines that operate on constrained tactical edge hardware. Working under the direction of the Principal AI/ML Engineer and program technical lead, the candidate collaborates closely with research scientists and software engineers to translate analytical findings into reproducible, well-documented ML experiments and pipeline components. The role requires strong Python and deep learning skills, comfort with real-world noisy sensor data, and the ability to work in air-gapped Linux environments without cloud infrastructure or GPU acceleration. Responsibilities: Design, build, and validate machine learning models for RF emitter identification — including feature engineering from sensor data, training pipeline development, model evaluation, and iterative refinement based on results Conduct hands-on exploratory data analysis on RF sensor datasets using Python and Jupyter notebooks — writing and running analytical code, characterizing feature distributions, identifying data quality issues, and producing documented findings Implement and maintain ML data pipelines — ingesting NDF sensor streams, applying rollup and preprocessing logic, constructing training datasets, and ensuring pipeline correctness on constrained edge hardware with no cloud dependency Collaborate with the technical lead and Principal AI/ML Engineer to investigate RF sensor data quality, attribution reliability, and feature behavior under contention — writing code to characterize error sources, validate assumptions, and reproduce findings Produce clear technical documentation of experiments, model configurations, and results — maintaining reproducibility through disciplined versioning, and contributing to monthly status reports and team knowledge sharing Career level with a complete understanding and wide application of machine learning principles and data science techniques. Working under general direction from the Principal AI/ML Engineer, executes independently on assigned modeling and analysis tasks, contributes to pipeline development, and produces reproducible, well-documented results. Bachelor’s or Master’s (or equivalent) with 5–7 years of hands-on applied experience. Required Skills: 5+ years of hands-on applied experience in machine learning, data science, or RF signal processing Demonstrated proficiency in Python for ML and data science work — PyTorch or TensorFlow for model development, Pandas/NumPy for data manipulation, and scikit-learn or similar for evaluation and baseline modeling Hands-on experience designing, training, and evaluating deep learning models — particularly metric learning, Siamese networks, or other similarity-learning architectures — on real-world, noisy, imbalanced datasets Practical experience handling real-world data quality problems — missing values, label noise, class imbalance, systematic bias, and sensor artifacts — and the ability to diagnose and address them without discarding valid data Ability to develop and run ML pipelines on Linux-based systems without cloud infrastructure or GPU acceleration — optimizing for CPU-only inference and multi-threaded data processing on resource-constrained x86 hardware Desired Skills: Familiarity with RF signal characteristics, passive receiver phenomenology, and sensor data interpretation — including awareness of processing artifacts, attribution ambiguities, and measurement limits common in signals intelligence datasets Hands-on experience applying machine learning — particularly metric learning, deep learning networks, or similarity-learning architectures — to RF or time-series signal data, including feature engineering, training pipeline development, and model validation Exposure to TDMA network protocols or military datalink systems, and interest in learning the signal processing challenges of dense, contested electromagnetic environments Familiarity with direction-finding, time-difference-of-arrival (TDOA), or related passive geolocation concepts — understanding of their mathematical foundations and common failure modes is more important than operational experience Experience with binary serialization formats (FlatBuffers, Protocol Buffers) and high-throughput sensor data pipelines operating in near-r