As a SENIOR MACHINE LEARNING ENGINEER would you like to work with cutting-edge technologies in a state-of-the-art data environment, while building a fintech from scratch and make the world a safer and better place at the same time?

Apply at TMNL! We offer you a very cool technical playground with all the latest technologies you need to create and accelerate our innovative, state-of-the-art transaction monitoring platform. A must-have to create the most effective detection and new insights, that will help banks, public sector and law enforcement to collectively defeat financial crime. Your responsibilities:

• Building production-grade, fully-automated model pipelines running on terrabytes of data
• This includes model monitoring, experiment tracking, creating reusable models and more
• Contribute to the development and population of our feature store
• Graph, machine learning or rule-based models? We’ve got them all!
• Your team has end-to-end ownership of your models: you build it, you run it, you maintain it.
• You’ll work in a cross-functional team consisting of Data Scientists, Domain Experts and Machine Learning Engineers.
• We’re cloud-native AWS, operating on a modeling platform built around SageMaker.
• Contribute to the MLE craft by sharing best practices and being an active member.
• Interface with Platform Teams (Data, MLOps) to influence the future direction of the modeling platform.

We expect you to be very advanced in Python plus:

• Multiple years experience building data-intensive products using Apache Spark
• Data-focused workflow orchestrators such as Airflow, Prefect and/or SageMaker Pipelines
• AWS (SageMaker, CodeBuild, CodePipeline, CloudFormation, Lambda, EventBridge)
• Terraform
• Docker
• Experience in implementing production-grade (machine learning) model pipelines working on large data sets, including a.o. testing, monitoring and drift detection.
• You know when to use notebooks, when not and how to go from a notebook to a pipeline
• You have shaped the engineering direction in a few projects previously
• You proactively engage in knowledge sharing activities, inside as well as across teams
• Experience working in a cross-functional model development team

Nice-to-haves:

• You have a hang for data pipelining and have spent a lot of time there
• AWS Glue
• Knowledge of / experience with MLOps principles and tools (model & data lineage, observability, feature stores, model registries…)
• Experience in the financial industry