Senior Machine Learning Engineer

About the role

We are looking for a Senior Machine Learning Engineer to design, build, and operate a unified ML infrastructure that bridges batch data in Snowflake with real‑time inference on Kubernetes. The role ensures high‑quality software engineering standards and reduces redundancy across data‑science squads.

Key responsibilities

• Design and maintain the core ML platform architecture, integrating Snowflake/Snowpark with Kubernetes for hybrid workloads.
• Deliver domain‑specific end‑to‑end data‑science products such as flight revenue forecasting, customer retention, and ground operations.
• Automate end‑to‑end ML pipelines—including data ingestion, model training, and continuous deployment—using Apache Airflow and GitLab CI/GitHub Actions.
• Build and manage a centralized feature store and model registry within Snowflake to keep training and serving consistent.
• Implement observability systems for model performance, data drift, and system health with Prometheus, Grafana, and Evidently AI.
• Develop reusable FastAPI or gRPC service wrappers for real‑time model serving.
• Establish “paved‑road” CI/CD, unit testing, and modular code workflows for the broader data‑science team.

Required profile

• Bachelor’s or Master’s degree in Computer Science, Software Engineering or a related field.
• Minimum 6‑8 years of experience in Data Science, MLOps, Platform Engineering or DevOps for machine learning, including 1‑2 years in the aviation domain.
• Deep expertise in machine learning, statistics and applied modeling.
• Strong understanding of production ML systems, trade‑offs and ability to influence architectural decisions.
• Fluent English communication and leadership skills to guide engineering culture without direct authority.

Required skills

• Python (object‑oriented, modular design) and SQL.
• Kubernetes, Docker and Infrastructure as Code with Terraform.
• Snowflake and Snowpark.
• Apache Airflow, GitLab CI and GitHub Actions.
• FastAPI or gRPC for model serving.
• Prometheus, Grafana and Evidently AI for monitoring.
• Modeling frameworks: LightGBM, XGBoost, TensorFlow, PyTorch.