MLOps Engineer

About the project 

We are recruiting for an advanced advertising ecosystem spanning smart devices across TV, mobile, and desktop. This project connects brands with TV audiences, building a cutting-edge advertising platform using machine learning to enhance targeting, personalization, and optimization, resulting in higher engagement and conversion rates.

During onboarding, you will learn about our products and services to identify the ideal customer persona based on demographics, psychographics, and purchasing power.

Join this international company to work on challenging projects with global teams. You will explore domains such as bidding, pacing, performance-based advertising, recommendations, and churn prediction/prevention.

As an MLOps engineer, you will work with unique proprietary data to address product challenges and build impactful solutions. Collaborate with talented engineers and machine learning researchers on state-of-the-art projects. Your role will involve designing, setting up, and managing infrastructure for deploying, monitoring, and maintaining ML models.

Do You have any questions? Write to sylwia.sochacka@antal.pl 

Role and Responsibilities

• Serve ML models to downstream applications, ensuring accessibility, scalability, and security.
• Design and develop scalable machine learning infrastructure to support high throughput and low latency.
• Manage model versions, ensuring the correct version is served to clients, and implement a rollback mechanism for issues with the current model version.
• Implement monitoring tools to track performance, health, and usage of the platform and its components. Monitor deployed model performance, addressing concept drift, data drift, and model degradation over time. Promptly identify and resolve issues to ensure system stability and responsiveness.
• Develop, test, deploy, and maintain data and model training pipelines to support our ML products.
• Integrate the serving infrastructure with other systems such as data pipelines, monitoring tools, and alerting systems, ensuring seamless communication and coordination.
• Continuously review and optimize the ML serving system, improving efficiency, reliability, and speed. Look for opportunities to simplify and automate tasks while maintaining high quality standards.
• Research the latest machine learning serving technologies (e.g., model compilers, GPU deployment, inference as a service) and stay updated with industry trends and developments.
• Streamline model deployment, unit testing, integration testing, stress testing, and shadow testing.
• Collaborate with ML engineers to deploy and serve production-grade, state-of-the-art machine learning models at scale.

Technologies in use 

●  Python

●  REST

●  AWS

●  Spark

●  Snowflake

●  Snowpark

●  Github Actions

●  Airflow

●  Kubernetes

●  Grafana

●  Terraform

●  TensorFlow

●  PyTorch

Skills and Qualifications

•  Minimum of 2 years of proven industry experience in microservices.

•  Experience with Infrastructure as Code tools (e.g., Terraform), cloud solutions, and orchestration tools (e.g., AWS, Sagemaker, Airflow, AWS Step/Lambda).

•  Familiarity with CI/CD tools (e.g., GitHub Actions), ETL processes, big data tools, and mainstream ML libraries (e.g., MapReduce, Spark, Flink, Kafka, Unix/Linux with shell, Docker, Kubernetes, TensorFlow, PyTorch, Spark ML).

•  Experience working with real-time monitoring and alerting tools (e.g., Prometheus, Grafana).

•  Proficiency in Python, Go, or other object-oriented programming languages.

•  Experience with distributed cache systems (e.g., Redis, Aerospike).

•  Degree in Computer Science or a related field.

Nice to have

•  At least 5 years of industry experience in developing low latency, high throughput distributed microservices and integrations (e.g., WS/REST).

•  Extensive experience in designing architectures for machine learning systems.

•  Proficiency with testing frameworks for online A/B testing, canary deployments, and blue-green deployments.

•  In-depth knowledge of ML serving technologies such as Seldon, Triton, ONNX, ONCL, TensorRT.

•  Experience in the advertising industry, including working with recommendation systems and the real-time bidding (RTB) ecosystem.

Join The Team and Enjoy Benefits!

•  Work with the latest technologies and access cutting-edge tools and platforms.

•  Participate in monthly team-building activities and enjoy a friendly, collaborative atmosphere.

•  Attend local and international conferences to expand your knowledge and network.

•  Benefit from flexible working hours to balance your personal and professional life.

•  Receive a high-performance workstation with 2 monitors and choose between Windows or Linux.

•  Enjoy private medical care, including free coverage for family members.

•  Stay active with a Multisport card and enjoy various fitness facilities.

•  Secure your future with comprehensive life insurance.

•  Benefit from a lunch card and a variety of discounts on products, theaters, and restaurants.

•  Unlimited free access to the Copernicus Science Center for you and your friends.

•  Test and experience new products before anyone else.

•  Work in a modern office located near the Metro station, with a hybrid work model offering three office days per week.

•  Receive an attractive relocation package if you're moving to join our team.

Apply now and be part of an innovative team that values your growth and well-being!

To learn more about Antal, please visit www.antal.pl