Machine Learning Engineer

At Thales, we know technology has the ability to make our world more secure, sustainable, and inclusive – and that it’s all driven by human intelligence.

Because it takes human intelligence to build and power the systems and solutions that people depend on every day. So we stay curious and make space for diverse points of view. We share what we know and we challenge what’s possible.

We’re driving progress in some of the world’s most important industries - from the bottom of the oceans to the depths of space and cyberspace - and from manufacturing to engineering, we work together to build a future we can all trust.

Imperva, a Thales company, is a globally recognized cybersecurity leader, dedicated to securing data and applications across diverse environments. Our cutting-edge solutions empower organizations to safeguard their most critical assets, ensuring robust protection against emerging threats.

We’re proud to be recognized as one of Israel’s Top 50 High-Tech Companies to Work For in 2024 (Dun & Bradstreet) and offer a flexible hybrid work model from our Tel Aviv office.

We are looking for a Machine Learning Engineer as part of our Threat Research group to help us deploy our ML models that protect our customers against cyber-attacks. The threat research group is composed of elite researchers & developers. We research application, DDoS & database attacks, provide algorithms and ML models for new products, and are leading innovation and thought leadership initiatives.

Key Responsibilities:

• Work together with Data Scientists, Data Engineers, DevOps, and Product teams to deploy ML models in production.
• Apply engineering knowledge and expertise to create robust and optimized ML applications that will perform under a set of predefined conditions.
• Play a major part in the development of innovative security solutions to be integrated in our best in breed products.
• Deploy ML models that will be capable of running offline, near real-time and real-time environments.
• Be part of building the infrastructure and pipelines for the ML lifecycle in production, from development to deployment and monitoring.
• Manage and monitor the ML infrastructure to maintain production grade performance.
• Ensure that our ML models in production remain accurate and reliable by implementing monitoring, testing, and validation tools and techniques.
• Introduce new features and capabilities into the ML infrastructure.
• Influence hundreds of millions of users, daily.
  
  

• B.Sc. in Computer Science, Engineering, Math, or other quantitative / technical field.
• 5+ years of hands-on experience working with advanced Python, including OOP, API frameworks, async and concurrency & parallelism.
• Deep understanding of the ML model lifecycle (training, testing, deployment etc.) and a basic understanding of model types and architectures.
• Practical experience working with and around machine learning models.
• Proven track record in building and managing ML pipelines.
• Experience working with task orchestration and MLOps tools such as AirFlow, Kubeflow, MLFlow, W&B, SageMaker etc.
• Familiarity with microservice methodology and container orchestration tools, such as Kubernetes.
• Experience with cloud-based data platforms such as AWS, GCP, or AZURE .
• Strong problem-solving skills and the ability to work both collaboratively with a team and independently.
• Self-learner with a can-do attitude.
• Solid experience in querying and manipulating large data sets using SQL and SQL like languages (e.g., Presto) - an advantage.
• Solid experience in machine learning and deep-learning libraries, such as Scikit-learn, SciPy, TensorFlow, Pandas, NumPy ,PyTorch, Keras – an advantage.
• Hands on programming skills in Java, C++, and Rust - an advantage.
• Experience deploying LLMs – an advantage.
• Background in cybersecurity – an advantage.