Machine Learning Engineer

What you'll do

• Own data and training infrastructure, including dataset workflows, distributed training, evaluation, and retraining loops.
• Deploy and optimize models for real-time inference on embedded hardware; build perception and multi-sensor models.
• Generate synthetic data and monitor runtime performance, drift, and model health; collaborate across autonomy and flight-test teams.

What they ask for

• Python for ML and tooling, plus production C++ on Linux; profiling, optimization, and rigorous testing.
• End-to-end ML data and training pipeline experience, including dataset construction, labeling/QA, augmentation, experiment tracking, and reproducible training.
• Hands-on PyTorch training and fine-tuning across detection, segmentation, and tracking architectures; edge deployment with model compression and runtime optimization.
• BS/MS/PhD in CS/EE/Robotics or similar, or equivalent experience, and a track record shipping ML models to production or hardware.

Nice to have

• Synthetic data generation and simulation with demonstrated sim-to-real transfer; EO/IR imagery or real flight/test data experience.
• Multi-modal perception and fusion; experience with CUDA, ROS 2, NVIDIA Jetson, drift monitoring, distributed training, or cloud ML platforms.

Pay

$120,000 — $160,000 USD (base salary); $165,000 — $220,000 USD (base salary)

Tools

Python, C++, Linux, DVC/Parquet, PyTorch, TensorRT/ONNX Runtime, SQL/Parquet, Jetson

AI focus

Develop and deploy perception and autonomy ML models, including detection, segmentation, tracking, search, classification/ATR, and multi-sensor fusion; create synthetic data and support sim-to-real transfer.