Data Science Engineer III

Description

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. While Fetcherr initially focused on the airline industry, the company is now expanding into additional verticals, bringing its dynamic AI-driven optimization capabilities to new industries such as travel, mobility, retail, e-commerce, and beyond.

About the Role

This is not a pure research role but one that is actively involved in building our product. You will be joining a team of Data Software Engineers and you will be directly contributing to code. You will own well- scoped modeling problems end to end, from exploring market data and designing features to validating models and getting them running in production, so that our pricing, inventory, and network optimization engines make better decisions in real time. This is a high-impact individual contributor role at the intersection of applied AI and production software, working directly with other data scientists, ML and data engineers, and product teams.

What you will do:

• Develop, validate, and iterate on demand forecasting, pricing, and optimization models using large-scale, high-velocity market data.
• Explore and analyze data from diverse internal and external sources to uncover signals, define features, and identify opportunities to improve model accuracy and business impact.
• Design and run offline experiments, backtests, and online evaluations to measure model performance and profit uplift.
• Write production-grade Python code and work with ML and data engineers to productionize models, ensuring they are reliable, observable, and cost-efficient.
• Monitor deployed models for drift, accuracy, and data quality issues, and troubleshoot and fix problems quickly.
• Keep our glass-box principles front and center: build models whose logic and outcomes can be explained to commercial teams and customers.
• Partner with product and commercial stakeholders to translate business problems into clear modeling approaches and communicate results.
• Contribute to the technical direction of the modeling stack as Fetcherr scales across new customers, verticals, and product lines.

Requirements

• 5+ years of full-time experience as a Data Scientist, Applied Scientist, ML Engineer, or similar role building models that run in production. Lab, proof of concept, prototype, academic, and part-time experience does not count toward this requirement.
• Strong programming skills in Python, with production-grade coding practices (testing, code review, version control).
• Solid foundation in statistics, machine learning, and time-series forecasting, with sound judgment on model validation and experiment design.
• Strong SQL skills and experience working with large relational and non-relational datasets.
• Experience and comfort with AI-assisted software development, along with the ability to write and reason about code yourself.
• Experience with cloud platforms (GCP and BigQuery preferred) and modern data warehouse and lakehouse technologies.
• Familiarity with orchestration tools (Airflow, Dagster) and CI/CD practices for ML and data pipelines.
• Strong analytical mindset and a pragmatic, get-it-done approach.
• Excellent collaboration and communication skills, comfortable working cross-functionally with engineering and product teams.

Nice to Have

• Experience with dynamic pricing, revenue management, or optimization problems.
• Experience in travel, e-commerce, logistics, or other real-time decisioning domains.
• Exposure to MLOps practices such as model registries, monitoring, and automated retraining.
• Experience with real-time OLAP engines such as ClickHouse.
• Experience in a Software-as-a-Service environment.