About this role
Responsibilities:
- Deploy ML models and AI pipelines from PoC through to scalable, reliable production, via CI/CD and orchestration
- Implement monitoring and maintenance strategies for deployed models
- Optimise models for inference speed and resource efficiency (TensorRT, OpenVINO, ONNX, pruning, quantisation)
- Perform data collection, cleaning and feature engineering to prepare datasets for training
- Collaborate with data scientists, engineers and product managers; maintain clear documentation
Qualifications:
- Bachelor's or Master's degree in Computer Science, Machine Learning, Data Science, AI or related field
- 5-9 years of relevant experience
- Proficiency in Python and libraries such as PyTorch, NumPy, Pandas and Scikit-learn
- Knowledge of model deployment/containerisation (Docker, Kubernetes) and SQL/NoSQL databases
- Familiarity with a cloud platform and MLOps tooling (MLflow, ClearML, etc.); edge deployment experience a plus