Machine Learning Engineer

Fetcherr builds responsible AI that transforms market complexity into measurable profit growth. At the core of the company is the Market Model - a proprietary AI-powered model delivering accurate, granular demand predictions with 96% forecast accuracy and real-time decision intelligence for commercial teams. Built on a glass-box architecture, it uses market data - not personal data - with full transparency into logic and outcomes. First deployed in global aviation, the technology is industry-agnostic and scales across volatile markets. Fetcherr delivers a consistent average profit uplift of 7%, with corporate partners including Delta, Virgin Atlantic, WestJet, Viva, and Azul.

The Large Market Modeling (LMM) team is the engine underneath Fetcherr's pricing intelligence. We're the ones who actually build and train the models — taking a chaotic world of market signals, customer behavior, and competitive dynamics and turning them into reliable, production-ready demand models. Other teams at Fetcherr work with the models; we're the ones who bring them to life. Think of us as the team that teaches Fetcherr's AI how people buy — so it can always recommend the right price at the right moment.

We are seeking a detail-oriented and collaborative Senior Machine L Engineer to help support and maintain our machine learning capabilities. This role is ideal for someone who enjoys working closely with production systems, ensuring reliability, scalability, and explainability of models while enabling research teams to deliver impact faster.

Responsibilities:

• Collaborate with cross-functional teams to ensure ML systems remain robust, explainable, and aligned with business needs.
• Monitor and report on ML model performance, reliability, and explainability metrics.
• Participate in model retraining procedures, implement automation and optimization of MLOps pipelines.
• Extend and scale monitoring pipelines, including support for new features in development.
• Investigate, troubleshoot, and resolve issues in production ML workflows (tiered support from initial triage to root-cause analysis with model owners).
• Develop and maintain repositories for feature engineering, inference monitoring pipelines, and artifact monitoring tools.
• Perform exploratory data analysis (EDA) on historical datasets to identify quality issues and maintain data health.
• Implement and oversee production based adjusters across customer deployments.
• Evaluate and track critical ML artifacts such as explainability files, coverage metrics, and alignment of features.
• Support development and maintenance of internal tools (e.g., interfaces, registries, and feature monitoring frameworks).
• Build and maintain static and temporal features, including seasonality, event-based, and price-related features.

Requirements

• 5+ years of hands-on experience in data science, ML operations, or applied ML support.
• Proficiency in Python and standard data/ML libraries (Pandas/Polars, NumPy, Scikit-learn, SQL; experience with PyTorch or TensorFlow is a plus).
• Strong data visualization and exploratory data analysis skills for monitoring and debugging pipelines.
• Experience with time-series data and feature engineering.
• Familiarity with explainability tools and model monitoring best practices.
• Strong problem-solving skills with the ability to troubleshoot across data, code, and model workflows.
• Excellent communication skills to summarize findings for both technical and non-technical audiences.
• Experience with cloud-based ML platforms - preferably GCP
• Familiarity with containerization (Docker), K8s, CI/CD workflows, or ML observability tools.
• Familiarity with orchestration tools such as Airflow, Kedro or Dagster is a plus.
• Prior exposure to demand forecasting, pricing, or revenue management.
• Bachelor's or Master's in Computer Science, Machine Learning, Statistics, Engineering or a relevant field.

If you’re excited about ensuring that machine learning systems are reliable, explainable, and production-ready in a fast-moving environment, we’d love to hear from you.