Machine Learning Engineer

Description du poste:

Welcome to Kanadevia Inova, a global innovation leader in the waste infrastructure space, where we believe in creating a sustainable future through technology and innovation.
Transforming Waste into Value
At Kanadevia Inova, we pride ourselves on being at the forefront of waste-to-X technology. We are not just waste managers; we are creators of value from what communities discard. Your role at Kanadevia Inova directly contributes to turning something once considered useless - waste - into something invaluable: energy, heat, hydrogen, fertilizer, and beyond.

* Industrialise and operate AI/ML solutions by transforming prototypes into scalable, production-ready applications.
* Design, implement, and maintain end-to-end MLOps pipelines covering training, validation, deployment, monitoring, and retraining.
* Collaborate closely with Data Scientists, Data Engineers, Software Engineers, Product Managers, and business stakeholders to deliver AI solutions.
* Ensure reliability, security, compliance, data integrity, performance, and governance throughout the machine learning lifecycle.
* Monitor and optimise model performance, troubleshoot production issues, and support continuous improvement while mentoring less experienced colleagues

Profil requis du candidat:

* MSc in Computer Science or a STEM field with a strong computer science focus, plus experience working in agile software development environments.
* Strong Python programming skills and hands-on experience with machine learning frameworks such as PyTorch, TensorFlow, or Scikit-learn.
* Solid understanding of MLOps practices, including model deployment, versioning, monitoring, and lifecycle management in production environments.
* Experience with cloud platforms (preferably Azure), containerisation technologies (Docker), APIs, databases, and distributed systems.
* Knowledge of data engineering and data processing frameworks; experience with industrial IoT, time-series data, computer vision, or Physics-AI solutions is advantageous