# Machine Learning Engineer, Detection and Tracking

**Company**: Helsing
**Location**: Washington, DC, DC
**Experience**: senior
**Job type**: full-time
**Category**: Engineering
**Industry**: Technology

**Apply**: https://job-boards.greenhouse.io/helsing/jobs/4953562101?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply
**Canonical**: https://yubhub.co/jobs/job_c547a376-cfa

## Description

Helsing develops artificial intelligence-enabled capabilities to protect and defend democracies. They build Altra, an AI-powered drone software platform, and HX-2, their autonomous drone.

You will own the detection and tracking models that power Helsing's products , training, tuning, and deploying models against US-specific datasets. This is an applied ML role: you won't be writing research papers, but you will be expected to have strong intuition for model performance, data quality, and the practical trade-offs involved in getting detection and tracking systems to work reliably in production.

Responsibilities:

- Train and fine-tune detection models (YOLO, DETR, Faster R-CNN, and similar architectures) on mission-specific datasets.

- Implement and improve multi-object tracking pipelines (SORT, DeepSORT, ByteTrack, or similar).

- Evaluate model performance: analyze metrics, diagnose failure modes, and iterate on data and model improvements.

- Manage the data pipeline end-to-end: assess raw data, coordinate annotation, curate datasets, and implement augmentation strategies.

- Optimize models for deployment on SWaP-constrained and embedded platforms (quantization, pruning, TensorRT, ONNX export).

- Collaborate with systems engineers to integrate models into the broader Altra platform.

- Work across sensor modalities as needed, including electro-optical, infrared, and other imaging sources.

Requirements:

- 5+ years of experience in applied machine learning or computer vision.

- Bachelor's degree in Computer Science, Electrical Engineering, or a related field; Master's or PhD strongly preferred.

- Production experience training and deploying object detection models , not just research or academic projects.

- Proficient in Python and PyTorch or a comparable deep learning framework.

- Strong intuition for data quality; ability to look at annotated datasets, training curves, and evaluation metrics and know what's wrong.

- Experience with the full model training lifecycle: data curation, annotation management, training, evaluation, and deployment.

- Experience optimizing models for deployment on SWaP-constrained and edge platforms (TensorRT, ONNX, quantization).

- Understanding of multi-object tracking and experience with tracking algorithms in practice.

- Ability to read and contextualize scientific papers in computer vision and apply findings to production systems.

- U.S. citizenship required.

Nice to have:

- Strong proficiency in Rust or C++ for production model deployment and optimization.

- Experience with multiple sensor modalities , particularly infrared or thermal imaging.

- Familiarity with MLOps tooling: experiment tracking (MLflow, Weights & Biases), dataset versioning, model registries.

- Experience with annotation tools and workflows (CVAT, Label Studio, or similar).

- Background in computer vision beyond detection , segmentation, pose estimation, activity recognition.

- Experience with simulators, emulators, or synthetic data generation for training and evaluation.

- Experience deploying models on GPU-accelerated embedded platforms (NVIDIA Jetson, similar).

- Background in defense, intelligence, or other mission-critical environments.

Benefits:

- A focus on outcomes, not time-tracking.

- A generous compensation and benefits package (in addition to base salary) that includes, but may not be limited to, insurance coverage (medical and travel), flexible paid time off, paid holidays, and remote and/or hybrid work available depending on position.

## Skills

### Required
- Python
- PyTorch
- YOLO
- DETR
- Faster R-CNN
- SORT
- DeepSORT
- ByteTrack
- TensorRT
- ONNX
- multi-object tracking
- computer vision
- machine learning

### Nice to have
- Rust
- C++
- infrared or thermal imaging
- MLOps tooling
- annotation tools
- CVAT
- Label Studio
- segmentation
- pose estimation
- activity recognition
- simulators
- emulators
- synthetic data generation
- GPU-accelerated embedded platforms
- NVIDIA Jetson

---

Source: [Apply at job-boards.greenhouse.io](https://job-boards.greenhouse.io/helsing/jobs/4953562101?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply)