Senior ML Engineer / ML Scientist - Fraud Detection

Job Description

Senior Machine Learning Engineer

\n

Remote, United States

\n

\n

Overview

\n

Harnham is partnering with a global technology company at the forefront of ecommerce fraud prevention and transaction intelligence . The organization provides machine learning driven technology that helps online retailers identify fraud in real time, approve more legitimate transactions, and reduce financial losses throughout the digital purchasing journey.

\n

\n

The platform supports approximately 1,000 merchants across more than 100 countries , processing billions of transactions annually. Its business model goes beyond traditional fraud detection by providing a financial guarantee on approved transactions , placing the performance of its machine learning technology directly at the center of the customer experience and the business.

\n

\n

Work Authorization

\n

This position is open only to U.S. citizens and U.S. lawful permanent residents (Green Card holders).

\n

\n

The employer is unable to provide or support employment visa sponsorship now or in the future, including H-1B, F-1 OPT, STEM OPT, CPT, TN, O-1, E-3, J-1, or other temporary or nonimmigrant work authorization.

\n

\n

Candidates who do not meet this requirement will not be considered.

\n

\n

The Role

\n

The Senior Machine Learning Engineer will join an established Machine Learning organization responsible for developing and operating the models that power real time fraud decisions across the platform.

\n

\n

This position combines applied machine learning, experimentation, statistical evaluation, and production engineering. You will own complex ML problems from initial exploration and model development through offline evaluation, deployment, monitoring, and continued optimization.

\n

\n

The team is seeking an engineer with strong machine learning fundamentals who can independently evaluate technical approaches, develop solutions from the ground up, and operate effectively within large scale distributed environments.

\n

\n

Responsibilities

\n

\n
• Design, develop, evaluate, and deploy machine learning models supporting real time fraud detection and transaction decisioning.
\n
• Develop experimental approaches to complex business and machine learning problems.
\n
• Build and enhance ML pipeline components that enable efficient, repeatable experimentation.
\n
• Develop rigorous offline evaluation methodologies to assess model performance prior to production deployment.
\n
• Evaluate model architectures, features, and statistical approaches to improve predictive performance.
\n
• Contribute to ensemble modeling approaches that combine multiple models into improved decision systems.
\n
• Build and operate distributed machine learning workloads using Python, SQL, and Spark .
\n
• Own models throughout the full lifecycle, including development, testing, deployment, monitoring, and optimization.
\n
• Partner with Product, Engineering, and Risk teams to translate business requirements into scalable technical solutions.
\n
• Establish and maintain high standards for testing, documentation, reproducibility, and model monitoring.
\n
• Provide technical leadership and contribute to the broader direction of the Machine Learning organization.
\n

\n

\n

Required Qualifications

\n

\n
• 4+ years of post undergraduate professional experience in a production machine learning environment.
\n
• Demonstrated experience independently developing machine learning solutions from experimentation through production.
\n
• Strong proficiency in Python and SQL .
\n
• Hands-on experience with Apache Spark and distributed computing environments .
\n
• Strong foundation in machine learning theory, statistics, experimental design, and model evaluation.
\n
• Experience designing and conducting machine learning experiments from the ground up rather than primarily fine tuning or integrating existing foundation models.
\n
• Experience developing offline evaluation frameworks and comparing multiple modeling approaches.
\n
• Experience deploying, monitoring, and improving machine learning models in production.
\n
• Ability to work independently on technically ambiguous problems while collaborating across engineering and business functions.
\n

\n

\n

Preferred Qualifications

\n

\n
• Master's degree or PhD in Computer Science, Statistics, Machine Learning, Mathematics, or a related quantitative discipline.
\n
• Strong academic or research background in machine learning or statistics.
\n
• Experience with ensemble modeling techniques.
\n
• Experience developing ML systems operating on high volume or real time data.
\n
• Experience within fraud detection, payments, ecommerce, transaction risk, or a related domain.
\n

\n

\n

Work Environment

\n

This position is fully remote within the United States . The team operates across U.S. time zones, with in-person travel expected approximately once per year.

\n

The Machine Learning organization consists of approximately 20 professionals working across three small, highly collaborative teams. Each team maintains end-to-end ownership of its services and the machine learning models supporting its product area.

\n

\n

Compensation & Benefits

\n

The anticipated base salary varies by geographic location and level, with compensation ranging from $140,000 to $210,000 across the United States. The organization has flexibility to offer up to $210,000 base for select profiles.

\n

\n

Additional compensation and benefits include:

\n

\n
• Annual performance bonus
\n
• Stock options
\n
• 401(k) match
\n
• Medical, dental, and vision coverage
\n
• Unlimited PTO
\n
• 12 weeks of paid parental leave
\n
• Life and disability insurance
\n
• Mental health and therapy benefits
\n
• Professional learning and development resources
\n

\n

\n

About Harnham

\n

Harnham is a specialist recruitment firm focused exclusively on Data, Analytics, Artificial Intelligence, and Technology. We are partnering directly with the hiring organization to identify experienced machine learning professionals for this opportunity.