Senior Machine Learning Engineer

Ravelin Technology

46d•Remote

About The Position

We are Ravelin, a fraud detection company using advanced machine learning and network analysis technology. Our goal is to make online transactions safer and help our clients feel confident serving their customers. We value work/life balance and embrace a flat hierarchy structure. You will learn fast about cutting-edge tech and work with some of the brightest and nicest people around. The Detection team is responsible for keeping fraud rates low and clients happy by continuously training and deploying machine learning models. We aim to make model deployments as easy and error-free as code deployments. Our models are trained to spot multiple types of fraud, using a variety of data sources and techniques in real time. The prediction pipelines are under strict SLAs; every prediction must be returned in under 300ms. The Detection team is core to Ravelin’s success. They work in a deeply collaborative partnership with the Data Engineering team to design the data architecture and infrastructure that powers our ML systems. We are looking for a Senior Machine Learning Engineer to join our Detection team. In this role, you will be setting the technical direction that bridges data science and engineering. You will be responsible for the architecture, scalability, and reliability of the high-performance ML systems that form the core of our fraud detection platform, with a critical focus on optimizing multi-GPU training for our foundational payments models (e.g., Transformers). Beyond just consuming data, you will take a leading role in defining how data is modeled, stored, and served, directly influencing the architecture of our feature generation pipelines and ensuring data quality throughout the ML lifecycle. You'll take strategic ownership of our ML infrastructure, championing platforms and tools that empower Data Scientists to rapidly experiment with novel data inputs and model architectures. Your day-to-day will involve close collaboration with engineers and data scientists to operate and optimize machine learning at scale, while also providing mentorship and guidance to other members of the team.

Requirements

Demonstrable experience designing, building, and deploying complex machine learning systems in a production environment.
Deep understanding of the full machine learning lifecycle, from research to deployment and a track record of leading the design and implementation of scalable training pipelines for large datasets.
Experience with deep learning frameworks like PyTorch or TensorFlow, including distributed/multi-GPU training and transformer architectures.
Familiarity with modern workflow orchestration tools such as Prefect, Kubeflow, Argo, etc.
Working experience leading complex, cross-functional projects and influencing technical direction across multiple teams.
Software engineering fundamentals, including data structures, design patterns, version control (Git), CI/CD, testing, and monitoring.
Exceptional problem-solving skills, with a proven ability to navigate ambiguity and lead technical deep-dives to resolve complex issues.
A collaborative mindset and strong communication skills with the ability to communicate to a range of audiences.

Nice To Haves

Proficiency in a systems programming language (e.g., Go, C++, Java, Rust).
Familiarity with data pipeline tools like dbt.

Responsibilities

Lead the design, architecture, and orchestration of scalable and reliable end-to-end ML pipelines – from raw data extraction and feature engineering to model training and inference.
Develop high-throughput data pipelines capable of handling terabyte-scale datasets efficiently and optimised for multi-GPU training of foundational transaction models (e.g., Transformers).
Propose and champion new machine learning methods and tools (including platforms that empower Data Science experimentation) to influence the technical roadmap and promote continuous innovation.
Drive cross-functional initiatives with Data Engineering, Infra, and other teams to align on data architecture and ensure our ML systems meet overarching business objectives.
Evolve our MLOps infrastructure, driving the strategy for model versioning, automated deployments, monitoring, and observability using modern tools like Prefect.
Mentor and guide other members of the team, fostering a culture of technical excellence and continuous improvement through code reviews, design discussions, and knowledge sharing.
Champion and contribute to the continuous improvement of our internal tools and engineering best practices.