Real-Time ML Platform Engineer for Fraud Detection

DataVisor; Canada; On-site; CAD 90,000 - 140,000; Full time

Benefits offered by this job

Stock Options

Commuter Passes

Paid Time Off

Catered Lunch and Dinner

Team and Company Outings

Job summary

DataVisor is seeking platform engineers to build a next-generation machine learning platform that combines unsupervised and supervised learning for real-time fraud detection. You will help improve core detection algorithms and automate training pipelines, while expanding streaming and database systems to scale data processing across large consumer services.

You will design and implement distributed real-time systems using technologies like Kafka, Flink, Spark, Hadoop, HBase, Cassandra, and

Qualifications

• 1-5 years of software development experience.
• Experience in Java, Shell and Python development.
• Excellent knowledge of Relational Databases, SQL and ORM technologies (JPA2, Hibernate) is a plus.
• Experience in Cassandra, HBase, Flink, Spark or Kafka is a plus.
• Experience with test-driven development is a plus.
• Experience in CUDA development is a plus.
• Worked on multithreaded applications.
• Experience in Kubernetes.
• Experience in Shell and Python

Responsibilities

• Build and optimize real-time distributed systems for fraud detection.
• Develop ML pipelines and data processing using Spark, Hadoop, Cassandra, and Kafka.
• Design and implement streaming and database architectures for scalable platforms.
• Work on expanding novel streaming and database systems to support ML models and real-time inference.

Skills

Java

Shell

Python

SQL

ORM (JPA/Hibernate)

Cassandra

HBase

Flink

Spark

Kafka

CUDA

Multithreaded programming

Kubernetes

Testing (TDD)

Tools

Spring Framework

Kafka

Flink

Spark

HBase

Job description

DataVisor is seeking platform engineers to build a next-generation machine learning platform that combines unsupervised and supervised learning for real-time fraud detection. You will help improve core detection algorithms and automate training pipelines, while expanding streaming and database systems to scale data processing across large consumer services.

You will design and implement distributed real-time systems using technologies like Kafka, Flink, Spark, Hadoop, HBase, Cassandra, and