Key skills
PythonSQLMachine LearningMLSparkCommunication
About this role
Harnham is partnering with a fintech that has built a leading fraud protection platform. They are seeking a Senior Machine Learning Engineer to own the end-to-end lifecycle of machine learning projects and build scalable ML pipelines for fraud detection.
Responsibilities:
- Own the end-to-end lifecycle of machine learning projects, from experimentation through deployment and production monitoring
- Build, maintain, and optimize production-grade machine learning models for fraud detection
- Design and implement scalable ML pipelines to enable rapid experimentation and model iteration
- Develop advanced feature engineering and statistical methodologies to improve model performance
- Collaborate with Product, Engineering, and Risk teams to translate business needs into ML solutions
- Contribute to model training, evaluation frameworks, and experimentation infrastructure
- Ensure robustness, scalability, and reliability of ML systems in high-volume production environments
- Drive best practices in testing, documentation, and model monitoring across the ML team
Requirements:
- 4–6+ years of experience in machine learning within production environments
- Strong foundation in machine learning theory, statistical modeling, and evaluation techniques
- Experience building and deploying supervised and unsupervised ML models at scale
- Proven track record of taking ML projects from research/prototype to production
- Proficiency in Python, SQL, and key machine learning libraries
- Experience working with distributed data processing tools such as Spark
- Strong communication skills, with the ability to explain technical insights to non-technical stakeholders
- Detail-oriented mindset with a focus on delivering measurable business impact
- Experience in fraud detection, fintech, payments, or e-commerce domains
- Advanced degree (Master's or PhD) in a quantitative field
- Passion for writing well-tested, production-quality code
- Interest in adversarial machine learning and combating fraud at scale