Lead Machine Learning Engineer

Sky UK; Hilcote; On-site; GBP 70,000 - 90,000; Full time

Job summary

A leading telecommunications company in the United Kingdom is seeking a highly skilled Lead Machine Learning Engineer to enhance personalised recommendation systems. The successful candidate will design, train, and optimise machine learning models focused on user personalisation while working closely with data scientists and engineers. This role involves constructing and maintaining data pipelines, deploying ML models in production, and leading A/B testing initiatives. Ideal candidates have advanced Python skills and knowledge of ML frameworks like TensorFlow and PyTorch.

Qualifications

• Advanced proficiency in Python and knowledge of ML libraries/frameworks.
• Experience using ML Training frameworks and Model Serving technologies.
• Strong understanding of recommendation system design and personalisation algorithms.

Responsibilities

• Design, train, and optimise machine learning models for user personalisation.
• Construct and maintain robust and scalable data pipelines.
• Deploy and supervise ML models in production environments.
• Lead the design and analysis of A/B tests and offline experiments.

Skills

Advanced proficiency in Python

Knowledge of ML libraries/frameworks (TensorFlow, PyTorch)

Strong understanding of recommendation system design

Exceptional communication and analytical problem-solving skills

Tools

TFX

Kubeflow Pipelines SDK

TensorFlow Serving

Triton

TorchServe

Job description

We are seeking a highly skilled Lead Machine Learning Engineer to advance our personalised recommendation systems by developing efficient, low-latency solutions that serve millions of users globally. The successful candidate will collaborate closely with data scientists, engineers, and product managers to design intelligent content recommendation mechanisms and drive the ongoing advancement of our Machine Learning Platform.

Responsibilities

• Design, train, and optimise machine learning models focused on user personalisation, encompassing recommendation engines, ranking algorithms, user segmentation, and content analysis.
• Construct and maintain robust and scalable data pipelines for feature engineering and model training utilising both structured and unstructured large-scale datasets.
• Deploy and supervise ML models in production environments, ensuring high availability, optimal performance, and continued relevance.
• Lead the design and analysis of A/B tests and offline experiments to evaluate model efficacy and support continuous improvement.
• Engage with multidisciplinary teams to align machine learning initiatives with business objectives and user needs.
• Evaluate emerging research in machine learning, deep learning, and personalisation for potential integration within existing systems.
• Demonstrated expertise in the full lifecycle of machine learning, from model development, deployment and serving to monitoring and maintenance.

Qualifications

• Advanced proficiency in Python and knowledge of ML libraries/frameworks (e.g., TensorFlow, PyTorch).
• Experience using ML Training frameworks (e.g., TFX, Kubeflow Pipelines SDK) and Model Serving technologies (e.g., Tensorflow Serving, Triton, TorchServe).
• Experience with high-volume data processing and real-time streaming architectures.
• Strong understanding of recommendation system design and personalisation algorithms.
• Familiarity with Generative AI and its applications in production settings.
• Exceptional communication and analytical problem-solving skills.
• Proven successful experience in mentoring less experienced engineers to improve their technical skills.