ML Engineer

The project is focused on developing and enhancing a travel technology platform that connects travel agencies and tour operators with a global network of suppliers.

Requirements

• Designing and maintaining scalable ML pipelines
• Building robust data ingestion, feature engineering, and model training pipelines to ensure reproducibility and production readiness
• Deploying and monitoring models in production
• Leading model serving (APIs, batch inference), track performance and data drift, and implementing automated retraining triggers
• Optimizing model efficiency and infrastructure
• Reducing inference latency and cost via quantization, pruning, GPU tuning, and distributed training (e.g., PyTorch DDP, Horovod)
• Establishing MLOps best practices across teams
• Implementig CI/CD for models, versioning (DVC/MLflow), and shared tooling (feature stores, templates) to accelerate delivery

Schedule

• 12:00-21:00 CET
• Office / Remote / Hybrid