Lead ML Engineer

About the role

We are seeking a Lead Machine Learning Engineer to design, build, and productionise models for our new matching platform. You will own key components of the ML platform while collaborating with data scientists, platform engineers, and product teams.

Key responsibilities

• Design and implement scalable feature pipelines within a data‑lakehouse architecture, including fallback flows and data quality checks.
• Develop ranking, scoring, and entity‑similarity models using PyTorch, TensorFlow or XGBoost, and work with data scientists on model improvements.
• Apply SHAP or similar techniques to generate interpretable explanations and reason codes for business and regulatory use.
• Build and maintain training, processing, and inference pipelines on AWS SageMaker, integrating with model registries and CI/CD workflows.
• Deploy low‑latency, real‑time inference endpoints, implement cross‑account AWS IAM access, and optimise runtime performance and cost.
• Implement monitoring for feature drift, concept drift, and telemetry dashboards, and support rollback/re‑deploy mechanisms.

Required profile

• Proven experience delivering production‑grade ML systems in a fast‑moving environment.
• Strong hands‑on technical ability with ownership of end‑to‑end ML lifecycle components.
• Ability to work primarily as an individual contributor while influencing design decisions.
• Excellent collaboration skills with data scientists, platform engineers, and product teams.

Required skills

• AWS SageMaker
• MLOps
• Feature engineering and data‑lakehouse architectures
• Feature‑store patterns
• PyTorch
• TensorFlow
• XGBoost
• SHAP (or similar explainability tools)
• AWS IAM (cross‑account access)
• CI/CD for ML workflows