Senior Machine Learning Engineer

About Smartnumbers

We are on a mission to stop fraud and improve customer authentication. Fraud is a huge problem affecting millions of people, it costs the UK nearly £7bn and represents 40% of all crime. Too often the solution has been to put in place cumbersome authentication processes that frustrate genuine customers, cause inefficiencies for organisations and fail to prevent fraud.

We are changing this by providing organisations with real-time insight into the risk of a caller. We combine patented machine learning technology with our deep domain knowledge to prevent contact centre fraud and streamline customer experience.

We recognise that we need to work together to fight fraud, that is why we have fostered strategic partnerships with leading global organisations like BT, Genesys and Nuance. Together, we protect the UKs largest retail banks, investment banks and emergency services. We also believe in developing our people and developing high performing teams, reflected by our ⭐ Platinum Investors in People accreditation, fewer than 5% of organisations achieve this level!

What you’ll be working on

As a Senior Machine Learning Engineer in our Platform Chapter (Team Turing), you will provide technical leadership in the design, build, and maintenance of highly scalable, robust ML platforms. You will focus heavily on cloud-based authentication and fraud detection systems using AWS SageMaker and other AWS services (e.g. EC2, S3, Lambda, CloudFormation, CloudWatch).

You will own and continuously refine our data pipelines and workflows for efficient data processing and storage, utilising Amazon Athena, Apache Iceberg, and Apache Spark among other tools. Beyond feature development, you will be responsible for key non-functional aspects such as performance, observability, reliability, and cost-effectiveness across our ML infrastructure.

While your primary focus is on platform engineering / MLOps / Software Engineering (80%), you may also be involved in model development work (20%) when required.

You will:

• Own the end-to-end lifecycle of ML pipelines, from data ingestion and feature engineering to deployment and monitoring of real-time inferences.
• Implement best-in-class MLOps practices, ensuring reproducibility, versioning, and automation of our model training and deployment processes.
• Build and monitor ML models, proactively addressing issues such as overfitting, underfitting, data leakage, and drift.
• Mentor mid-level and junior engineers, guiding them on ML platform best practices, code quality, and agile delivery.

What technologies will I be using?

All of our teams are given the freedom and authority to pick their own stack based on their preferences. Our technology vision and strategy encourages you to try the latest innovations and we love serverless architectures. We value clean, maintainable and robust code for our business critical systems. Some of the technologies currently used by the Intelligence Group are listed below – while mastery of all these areas isn’t required, familiarity with as many as possible will be advantageous.

Cloud and Infrastructure Management

• Amazon CDK and Infrastructure as code
• Amazon SageMaker and SageMaker Studio for ML work
• Apache Iceberg, AWS Glue, Athena for data processing

Machine Learning and MLOps

• ML Frameworks: TensorFlow, PyTorch, Keras, Scikit-Learn
• ML Algorithms: Decision Trees, XGBoost, Deep Learning
• Model Explainability: SHAP explanations

Programming and Development Tools

• Python (NumPy, Pandas, Matplotlib, Scikit-Learn, SciPy)
• SQL

Deployment and CI/CD Pipelines

• GitHub
• Docker
• CircleCI

Telephony

• SIP/VoIP
• CCaaS (Contact Centre as a Service, e.g. Amazon Connect, Genesys)

What you’ll need for the role

We value people who are honest, supportive, passionate, learn fast, have a growth mindset, enjoy solving complex engineering problems, and are willing to challenge the status quo without fear of failure.

• Collaborative approach to working, preferring to discuss and brainstorm tasks with the rest of the team rather than working independently.
• Able to provide technical leadership on complex initiatives, own tasks end-to-end, and take responsibility for the quality of team deliverables.
• More interested in finding good solutions, increasing knowledge, and communicating results than simply working fast or producing lots of code.
• Deep understanding of object-oriented design fundamentals (clean code, SOLID principles, design patterns).
• Excited to learn new concepts, frameworks, languages, and services, and how to apply them.
  Comfortable optimising system performance, troubleshooting advanced issues in large-scale data pipelines, and driving performance improvements.
• Significant experience with cloud services (preferably AWS) and infrastructure as Code (e.g. CDK, CloudFormation, TerraForm).
• Proven track record of building and maintaining scalable data pipelines and ML platforms in production.
• Familiarity with containerisation (Docker) and CI/CD tools.
• Ready to lead or assist with ML model development and deployment when required, including advanced troubleshooting and performance tuning.

As a Senior Machine Learning Engineer within Team Turing, you’ll need to:

• Provide technical leadership in designing and implementing production-grade machine learning platforms, including the data engineering and infrastructure to train, deploy, and run inferences against models.
• Drive advanced MLOps best practices and tooling to elevate our machine learning infrastructure, focusing on reproducibility, reliability, and scalable CI/CD.
• Develop robust data pipelines, explore data, and perform feature engineering for large-scale datasets.
• Ensure system reliability and performance through effective monitoring and alerting, lineage tracking, and proactively addressing bottlenecks and cost optimisations.
• Mentor and guide mid-level ML engineers, reviewing code, sharing knowledge, and championing best practices to improve team capability.
• Take full responsibility for the validation, ongoing support, and maintenance of platform components, ensuring continuous improvement.
• Embrace Object Oriented best practices & principles in software engineering, such as clean code, SOLID principles, refactoring, design patterns, unit/integration testing, CI/CD.
• Shape the technical direction of our ML platform, contributing to architectural decisions, evaluating new tools, and proposing innovations that drive the future of our ML systems.

What we can offer you

As well as a competitive salary circa £85,000, we also offer a comprehensive benefits package, covering a variety of areas, both professional and personal. These benefits include:

• Hybrid working style, with the expectation of only one day in the office (with a great Central London office base!)
• Family friendly benefits including paid parental leave policies
• An extensive health insurance policy for you, with an option to add your family members
• A workplace pension with Aegon
• Life insurance of 4 x your salary
• A discretionary annual bonus of up to 10% of your salary
• An annual home office station allowance of £200, to help you set up a comfortable remote office space.
• A training allowance to support your continuous professional development.
• Weekly self-development time to spend exploring your professional development interests
• 25 days of annual leave (plus bank holidays), your birthday off, and an opportunity to buy up to 5 days annual leave per year
• Monthly company socials in the office
• A holistic wellbeing support plan encompassing a variety of offerings to assist you. We provide you with a monthly £50 allowance to fund activities to best support your wellbeing as well as workshops and training to provide tools and guidance. Additionally, there is a wide-ranging employee assistance programme available to advise on personal, family or financial matters, and also fun social events all year round.

Smartnumbers is committed to promoting equal opportunities in employment. You will receive equal treatment regardless of age, disability, neurodiversity, gender, gender identity, gender reassignment, marital or civil partner status, pregnancy or maternity, race, colour, nationality, ethnic or national origin, religion or belief, sex and sexual orientation. We welcome all applications for this role.

We are committed to providing reasonable support/adjustments in our recruiting processes. If you need support, please reach out to the hiring team.