AI / ML Engineer - Time Series Robotics

Excellent opportunity for an experienced
AI / ML Engineer
who will design, develop, and deploy advanced machine learning models for multi-sensor time-series data across robotic and vehicle platforms.

You will collaborate closely with robotics, controls, and embedded engineering teams to bring intelligent algorithms from concept to deployment, shaping the next generation of automated systems.

If you enjoy solving real-world problems with machine learning and want to influence next-generation intelligent platforms, this role provides an exciting and meaningful challenge.

Key Responsibilities:

• Develop ML models for time-series sensor data such as IMUs, currents, torques, joint states, and vehicle signals.
• Build scalable pipelines for data collection, preprocessing, feature extraction, and labeling.
• Prototype algorithms in Python (PyTorch, TensorFlow) and work with embedded teams to optimize models for deployment.
• Evaluate model performance using rigorous metrics and continuously refine models for real-world robustness.
• Translate engineering and system requirements into well-scoped ML problems and solutions.
• Support visualization tools, dashboards, and interfaces for stakeholders to interpret model outputs.
• Document datasets, experiments, models, and results to ensure full reproducibility.

**What You Bring

Required:**

• Bachelor’s, Master’s, or PhD in Computer Science, Electrical Engineering, Applied Mathematics, or related fields.
• Strong experience applying ML to time-series or sensor-based data.
• High proficiency in Python and ML frameworks such as PyTorch or TensorFlow.
• Experience working with real-world noisy datasets (automotive, robotics, industrial, IoT).
• Strong data science foundations: NumPy, Pandas, Jupyter, etc.
• Ability to work cross-functionally and communicate complex concepts clearly.

Preferred:

• Embedded / edge AI experience, including compression and optimization techniques.
• Background in robotics, control systems, or vehicle dynamics.
• Familiarity with MLOps tools (MLflow, experiment tracking, CI/CD for ML).
• Prior experience in R&D or multi-disciplinary product environments.