SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Helsing develops AI-enabled capabilities to protect and defend democracies, building Altra (an AI-powered drone software platform) and HX-2 (an autonomous drone). You will own the detection and tracking models that power these products, managing the full model lifecycle from data assessment and curation through annotation, training, evaluation, and deployment to edge platforms.
Your day-to-day work includes training and fine-tuning detection models (YOLO, DETR, Faster R-CNN, and similar architectures) on mission-specific datasets. You'll implement and improve multi-object tracking pipelines (SORT, DeepSORT, ByteTrack, or similar), evaluating model performance by analyzing metrics, diagnosing failure modes, and iterating on data and model improvements. You'll manage the data pipeline end-to-end: assessing raw data, coordinating annotation, curating datasets, and implementing augmentation strategies.
A key part of the role is optimizing models for deployment on SWaP-constrained and embedded platforms using quantization, pruning, TensorRT, and ONNX export. You'll collaborate with systems engineers to integrate models into the broader Altra platform and work with product and mission teams to understand requirements and validate performance in operational contexts.
This is an applied ML role focused on practical results rather than research. You'll need strong intuition for model performance, data quality, and the trade-offs involved in getting detection and tracking systems to work reliably in production. The company is growing its US operations with a team of mission-driven professionals tackling challenging problems in defense technology.
