ML and robotics engineer, four years across robot control, perception and model inference. M.Sc. student in Mechanical Engineering (Robotics) at the University of Manitoba, Winnipeg; B.S. Mechanical Engineering, NUST.
My research is markerless teleoperation of a 7-DoF manipulator (Kinova Gen3): RealSense and MediaPipe RGB-D perception at 100 Hz driving the arm in real time, with occlusion and dropout handling, gesture intent detection, a Genesis digital twin with payload estimation, and a 1 kHz C++ torque controller and safety layer underneath. That code is not public yet.
I also built a causal audio-visual emotion recognition model for real-time streaming: 75.9% accuracy at 6 ms per step, distilled from an offline model (paper accepted at GLOBCER).
| Project | What it is |
|---|---|
| gauntlet | Regression testing and failure analysis for learned robot policies. Runs a policy across seeded grids of perturbations (lighting, camera pose, clutter, latency, sensor corruption, dust, glare) on MuJoCo, PyBullet, Genesis or a numpy crop-row env, and reports where it fails, with confidence intervals and paired comparisons. On PyPI as gauntlet-robotics. |
| flux | FP8-quantized FLUX.1-schnell inference pipeline, tuned for fast generation on an RTX 4090. |
| Chicken-disease-classification-project | End-to-end image classifier: DVC pipeline, VGG16 transfer learning, Flask serving, Docker and CI/CD. |
| face_detection / kivy-app | Siamese-network face verification, and a Kivy desktop app that runs it on a webcam. |
Classical ML projects
| Project | What it is |
|---|---|
| Online-Payments-Fraud-Detection | Decision-tree classifier flagging fraudulent mobile-money transactions. |
| Stock-price-LSTM | Stock price forecasting with an LSTM. |
| Future_Sales_Prediction | Sales prediction from ad spend across platforms. |
| Waiter_Tips_Prediction | Linear regression predicting restaurant tips, with Plotly exploration. |
| Pfizer-Vaccine-Sentiment-Analysis | VADER sentiment scoring and word clouds on Pfizer vaccine tweets. |
| winequality-prediction | ElasticNet on red wine quality, with a DVC pipeline, Flask serving and CI. |
- Research Assistant, Robot Control and Safety, University of Manitoba (2024–present)
- Robotics Engineer, Teleworker AI (2026): ROS 2 scanning pipeline on a Unitree Go2, running on the onboard NVIDIA Jetson Orin
- ML Engineer, Wombo (2024): SDXL and FLUX inference optimization
- Freelance ML Engineer (2022–2024)
- Site and CV: hussain1.me
- LinkedIn: hussain-ai-robotics
- Email: mhussainahmad@outlook.com



