Senior Machine Learning (ML) Engineer

Anduril Industries is a defense technology company with a mission to transform U.S. and allied military capabilities with advanced technology. By bringing the expertise, technology, and business model of the 21st century’s most innovative companies to the defense industry, Anduril is changing how military systems are designed, built and sold. Anduril’s family of systems is powered by Lattice OS, an AI-powered operating system that turns thousands of data streams into a realtime, 3D command and control center. As the world enters an era of strategic competition, Anduril is committed to bringing cutting-edge autonomy, AI, computer vision, sensor fusion, and networking technology to the military in months, not years. ABOUT THE TEAM Anduril's Air Missile Defense Radar team develops cutting-edge tracking algorithms and software systems that detect, track, and characterize airborne threats in real-time. We're building the next generation of tracking intelligence capabilities—automated analysis systems that understand tracking performance, identify failure modes, and continuously improve our algorithms through data-driven insights. This role sits at the intersection of ML engineering and tracking domain expertise. You'll build end-to-end pipelines that ingest tracking algorithm telemetry, analyze correlation failures and performance anomalies, train models to automate root cause analysis, and deploy production tools that help engineers ask questions like "why didn't track X and track Y associate?" We don't just track targets; we track our tracking systems and make them smarter. WHAT YOU'LL DO Own tracking intelligence infrastructure end-to-end : Build the platform for ingesting tracking algorithm telemetry (hypotheses, scores, gains, association decisions), feature engineering performance metrics, training analysis models, and deploying them into production Automate tracking analysis : Develop ML models that identify correlation failures, track quality degradation, and root causes for tracking anomalies—replacing manual deep-dive investigations with scalable automated insights Build autotuning capabilities : Create systems that recognize incoming data characteristics and automatically adjust tracking algorithm parameters, frame rates, and model configurations for optimal performance Design human-in-the-loop tools : Build interfaces and query services that let engineers ask natural questions about tracking behavior and get data-driven answers backed by your models Exploit tracking telemetry : Instrument C++ tracking algorithms with appropriate logging (working with platform engineers), then marshal that data into consistent formats for analysis and model training Deploy in constrained environments : Package and deploy models for air-gapped systems with no external connectivity, following security scanning requirements where ML models are treated as data artifacts Manage the ML lifecycle : Handle data catalogs, ground truth labeling, model registries, versioning, and validation—ensuring models improve tracking performance in measurable ways Bridge domains : Translate between tracking algorithm fundamentals (Kalman filters, data association, multi-hypothesis tracking) and ML/data science techniques to build solutions that actually work Drive make/build decisions : Evaluate when to build custom models vs. leverage existing ML capabilities, selecting appropriate algorithm architectures for tracking intelligence problems Work hands-on-keyboard : This is a one-person show initially—you'll architect, code, deploy, and iterate rapidly using modern Python-based ML tooling REQUIRED QUALIFICATIONS 3+ years of experience with a strong mix of ML engineering and data science—you've built models AND deployed them into production systems Proficiency in Python and modern ML frameworks (PyTorch, TensorFlow, scikit-learn) Experience with MLOps practices: data pipelines, feature engineering, model versioning, experiment tracking, and de ... (truncated, view full listing at source)