Madfish
Description
About the Role You will be part of the Engineering team, driving the evolution of Batch AI, our AI-powered system that optimizes material feeding in concrete production. Batch AI combines sensor data with predictive and machine learning models to make batching operations more accurate, consistent, and autonomous. As a Senior ML Engineer, you will apply machine learning engineering and applied data science techniques to design, train, and evaluate models that directly impact industrial performance, working closely with engineers and the Product Operations team. This is a hands‑on role for someone who thrives on ownership, experimentation, and delivering real‑world impact. You will play a key role in advancing the intelligence and reliability of industrial processes powered by Batch AI.
Requirements Qualifications Must‑Have
BSc or MSc in Data Science, Applied Mathematics, Computer Science, or equivalent practical experience.
5+ years of hands‑on experience in applied machine learning, with a focus on regression, forecasting, or optimization.
Proven experience in production‑grade ML pipelines, from experimentation to deployment.
Strong grasp of data science concepts such as cross‑validation, quantile modelling, and model safeguard techniques.
Strong background in Python and data science libraries, with the ability to write clean, efficient, and production‑ready code.
Experience using modern development tools and practices, including Git, code review processes, automated testing, and CI/CD pipelines.
Solid understanding of data lifecycle management, including time‑series feature engineering and retraining strategies.
Experience with ML model monitoring, versioning, and continuous retraining frameworks.
Familiarity with cloud ML ecosystems (Azure or AWS).
Comfortable documenting and presenting analytical findings to mixed technical and non‑technical audiences.
Effective communication and collaboration skills.
Self‑driven, organized, and able to deliver with minimal supervision.
Nice‑to‑Have
Experience with Azure ML, CosmosDB, Service Bus, and Kubernetes.
Experience with AWS SageMaker, ECS Fargate, SQS/EventBridge, and DocumentDB.
Exposure to industrial data from manufacturing equipment, batching systems, or other IoT‑connected process control environments such as manufacturing, logistics, or energy sectors.
Experience applying software development and engineering best practices, including architectural, design, and coding principles.
Experience with containerised workloads (Docker).
Job responsibilities
Design, train, and validate machine learning models that improve process performance and stability in concrete batching operations.
Lead end‑to‑end model development, from data exploration and feature engineering to deployment and validation.
Define and implement retraining and validation strategies that ensure continuous performance improvement.
Work closely with engineers to ensure models integrate efficiently with production systems in Azure and AWS environments.
Propose data selection and quality control methods to improve training representativity.
Contribute to the monitoring and evaluation approach for ongoing model health.
Document methodologies, experiments, assumptions, and decisions to maintain clarity and reproducibility.
Collaborate with team members, the Product Operations team, and other stakeholders as needed to support large‑scale deployment.
#J-18808-Ljbffr
Requirements Qualifications Must‑Have
BSc or MSc in Data Science, Applied Mathematics, Computer Science, or equivalent practical experience.
5+ years of hands‑on experience in applied machine learning, with a focus on regression, forecasting, or optimization.
Proven experience in production‑grade ML pipelines, from experimentation to deployment.
Strong grasp of data science concepts such as cross‑validation, quantile modelling, and model safeguard techniques.
Strong background in Python and data science libraries, with the ability to write clean, efficient, and production‑ready code.
Experience using modern development tools and practices, including Git, code review processes, automated testing, and CI/CD pipelines.
Solid understanding of data lifecycle management, including time‑series feature engineering and retraining strategies.
Experience with ML model monitoring, versioning, and continuous retraining frameworks.
Familiarity with cloud ML ecosystems (Azure or AWS).
Comfortable documenting and presenting analytical findings to mixed technical and non‑technical audiences.
Effective communication and collaboration skills.
Self‑driven, organized, and able to deliver with minimal supervision.
Nice‑to‑Have
Experience with Azure ML, CosmosDB, Service Bus, and Kubernetes.
Experience with AWS SageMaker, ECS Fargate, SQS/EventBridge, and DocumentDB.
Exposure to industrial data from manufacturing equipment, batching systems, or other IoT‑connected process control environments such as manufacturing, logistics, or energy sectors.
Experience applying software development and engineering best practices, including architectural, design, and coding principles.
Experience with containerised workloads (Docker).
Job responsibilities
Design, train, and validate machine learning models that improve process performance and stability in concrete batching operations.
Lead end‑to‑end model development, from data exploration and feature engineering to deployment and validation.
Define and implement retraining and validation strategies that ensure continuous performance improvement.
Work closely with engineers to ensure models integrate efficiently with production systems in Azure and AWS environments.
Propose data selection and quality control methods to improve training representativity.
Contribute to the monitoring and evaluation approach for ongoing model health.
Document methodologies, experiments, assumptions, and decisions to maintain clarity and reproducibility.
Collaborate with team members, the Product Operations team, and other stakeholders as needed to support large‑scale deployment.
#J-18808-Ljbffr