MACHINE LEARNING ENGINEER

Description.
• What we are looking for / tasks associated with the position.
We are seeking a highly motivated Machine Learning Engineer with expertise in designing and implementing scalable ML pipelines, infrastructure, and CI/CD workflows.
The ideal candidate will contribute to building robust data and ML systems, ensuring scalability, reproducibility, and operational excellence in analytics projects.
Key Responsibilities.
1.
Pipeline Design and Implementation o Design and implement training pipelines for machine learning models, including environment configuration, data profiling, and distribution maintenance.
o Develop inference pipelines for batch and online predictions.
o Establish robust CI/CD pipelines for analytics workflows leveraging MLOps practices.
2.
Model Monitoring and Maintenance o Design schemes for monitoring model performance during inference phases, including data drift detection (online) and model drift analysis (offline).
3.
Feature Engineering and Analytics o Apply advanced feature engineering techniques and machine learning principles to extract insights and build effective models.
4.
Collaboration and Documentation o Work collaboratively with global teams to ensure effective delivery of ML systems.
o Document all processes, including environment configurations, access rules for datasets, and model monitoring schemes, to ensure traceability and reproducibility.
• Must have.
- Degree in Software Engineering or Computer Engineering or similar - Good written and verbal communication skills - Ability to work in a collaborative environment and with global teams - Ability for critical analysis and focused on problem solving - Commitment to quality of deliveries - Knowledge of languages (written and oral).
English - Technical knowledge of SQL, Python or Scala and related Machine learning packages - Technical knowledge of Spark in Python or Scala, namely RDD and Dataset APIs - Knowledge in designing training and model calibration flows (ML pipelines) including package environments, infrastructure, data profiling during training and verifying the maintenance of your distribution (profile checking) - General knowledge of the principles of infrastructure elasticity, reproducibility and traceability in ML pipelines, rules for accessing datasets in these ML pipelines, monitoring of Inference pipelines - Knowledge in designing inference flows, namely batch inference and online inference - Knowledge in designing CI/CD pipelines for Analytics with MLOps - Knowledge in designing model monitoring schemes during the inference phase, namely data drift (online) and model drift (offline) - General knowledge of Feature Engineering and Machine learning techniques • Nice to have.
- Knowledge of the Energy & Utilities market and GDPR - Knowledge of Agile methodology, JIRA and Confluence tools - Knowledge of languages (written and oral).
Portuguese, Spanish - • Top Skills.
- Proficiency in SQL - Proficiency in Python - Proficiency in Scala - Proficiency in Apache Spark - Expertise in ML Pipelines, MLOps practices and monitoring techniques - Strong knowledge of feature engineering, data profiling, and pipeline reproducibility - Understanding of elastic infrastructure for scalable machine learning applications - Strong analytical skills for designing robust and scalable ML workflows • Years of Experience.
up to 5 years of experience in the role for the service to be contracted • Type of project.
Development • Hybrid Position Client's sector.
Energy