Senior ML Engineer

Description

The company is a global partner for AI-first digital transformation and engineering, with over 25 years in the market and about 5,000 staff across 16 countries.

It works across AI, data and cloud, intelligent automation and digital products.

Its CEE unit has nearly 1,000 specialists building applications, data platforms and AI solutions on AWS, Azure, GCP, Databricks and Snowflake, pairing engineering depth with a consulting approach.

Responsibilities

• Take over an existing ML solution and codebase once the Lead AI/ML Engineer has handed over knowledge.
• Build and put into production models that make first-order recommendations for new products.
• Create and run training and inference pipelines in Azure Machine Learning.
• Set up scheduled retraining and connect the models to the current model registry and validation gate.
• Add data quality and completeness checks, including checks on the product attributes the models need.
• Write recommendation logic that accounts for service levels, minimum order quantities, time to the next delivery and category-based fallback rules.
• Move products from the new-item model to the main forecasting model and validate the switch once enough sales history exists.
• Extend daily recommendations to eligible catalogue products using agreed criteria and backtesting results.
• Support the phased catalogue rollout and monitor individual product segments.
• Maintain MLOps: model versioning, validation, automated retraining, monitoring, data-drift detection and alerting.
• Connect ML outputs to the existing data warehouse and Power BI reports.
• Make production runs reproducible, keeping each model version's training window and feature contract.
• Take part in testing, dry runs, parallel runs, documentation and operational handover.
• Work with the Lead AI/ML Engineer, the BI team and business stakeholders to make the production rollout reliable.

Requirements

• You have hands-on experience building and productionizing ML solutions.
• You have worked with Azure Machine Learning, including training and inference pipelines.
• You have applied MLOps practices such as model registries, versioning, automated retraining, validation gates, monitoring and rollback.
• You have built and run scheduled batch ML pipelines.
• You can take over an existing ML codebase and keep developing it after a knowledge transfer.
• You have connected ML pipelines to data warehouses and built data validation and input-quality checks.
• You have monitored models and detected data drift.
• You have set up automated testing and CI/CD for ML workloads.
• You are comfortable with Git-based repositories and deployment workflows.
• You understand model evaluation, backtesting, champion/challenger validation and production acceptance criteria.
• You document ML systems and operational procedures.
• You work well with technical teams and business stakeholders.
• You can implement work independently after an initial knowledge transfer period.
• You have worked on demand forecasting, inventory optimization, or purchasing and replenishment systems.
• You have used LightGBM.
• You have worked with Azure SQL-based data warehouses.
• You know Azure managed identities, Key Vault and Azure Monitor.
• You know Power BI integrations and ML monitoring and reporting use cases.
• You have used Azure DevOps or GitHub Actions along with Azure deployment workflows.
• You have worked with service-level-based inventory or order-quantity models.
• You understand model calibration and how to monitor forecast accuracy and bias.
• You have built ML solutions for new-product forecasting with limited historical data.
• You know retail, wholesale, supply chain or catalogue-based business environments.

Conditions

You will be available for an approximately 15-week MVP, with an expected commitment of around 45 engineer-days.

The hiring process runs in five steps: CV review, HR call, interview, client interview, then decision.