Machine learning engineer for customer engagement

As a Machine Learning Engineer at Iterable, you will design and build the end-to-end machine learning systems that power intelligence across our product. As a high-tech marketing platform, we work with thousands of large-scale and diverse enterprise customers. The scale and diversity of these workloads — supporting personalization with deep customizability — present unique and exciting challenges for machine learning at production scale. You will have real autonomy: from research and experimentation through to models running reliably in production, you'll own the systems and models behind our ML products and help shape the direction of AI at Iterable.

• Contribute to core product features, including send-time/frequency optimization, recommendation engines, and campaign personalization.
• Perform EDA, feature engineering, distributed training, production deployment, latency monitoring, and online experimentation (e.g., A/B testing, multi-armed bandits, ensemble models).
• Build and maintain scalable data pipelines and serving architectures using Databricks, Spark, AWS, Ray, and Kubernetes.
• Partner with Backend and Platform teams to integrate feature serving, improve data architecture, and adhere to team engineering standards.
• Participate in design reviews, expand your domain knowledge, and continuously improve code quality across our repositories.
• Integrating and evaluating new models that add intelligence to our core product offerings.
• Enhancing algorithmic models that optimize the send time and frequency of outgoing marketing campaigns.
• Designing reliable data pipelines to accelerate feature extraction and model iteration.
• Working with platform engineers to enhance feature- and model-serving latency.
• Benchmarking and tuning multi-armed bandit algorithms.
• Developing internal tools to inspect, visualize, and debug features and models.

• 2–4 years of hands-on MLE experience deploying models into production environments.
• Practical experience building and optimizing production data pipelines using Databricks and Spark.
• Solid background in training, evaluating, optimizing, and serving machine learning and deep learning models in production.
• Proficiency in Python and/or Scala with a strong focus on clean, modular, tested, and maintainable code.
• Hands-on experience with containerization (Docker, Kubernetes), distributed compute frameworks (Ray or Spark), and microservices.
• Focus on customer impact, serving latency, and reliability alongside algorithmic performance.
• Будет плюсом: Experience with large-scale recommendation systems or personalization engines; Familiarity with Feature Stores (e.g., Feast, Tecton) or ML observability platforms (e.g., Evidently, Arize); Exposure to Infrastructure-as-Code (Terraform, Pulumi) and CI/CD pipelines

• Competitive salaries & meaningful equity
• Private Medical Insurance
• Life/Risk Assurance
• Meal Allowance: 8.55€ per day
• Community Days (days for us to give back to the community)
• Paid Annual Leave (22 days)
• Global Lifestyle Reimbursement Account
• Paid Sabbatical
• Complete laptop workstation
• The base salary range for this position in Lisbon, Portugal, is €55,000 – €68,000 per year (gross).