Senior Machine Learning Engineer, Supply & Competitive Intelligence

Darum lohnt es sich

Responsibilities Design and deploy ML models that extract and structure competitive intelligence signals — supply availability, pricing patterns, and market saturation — from large-scale crawled datasets across global competitors Build and maintain end-to-end ML pipelines spanning feature engineering, offline training, and low‑latency online serving, ensuring high data fidelity and resilience to upstream schema drift Apply entity resolution and matching techniques to accurately map competitor listings and markets to Airbnb's internal supply taxonomy, using methods such as embedding models, gradient‑boosted trees, and transformer‑based architectures Partner with the crawling infrastructure engineer, data engineers, and product teams to translate competitive intelligence needs into well‑defined ML problem formulations and measurable success criteria Run rigorous offline and online experiments to evaluate model quality, and collaborate with Pricing, Supply Growth, and Strategy stakeholders to turn model outputs into actionable business decisions Stay current with the latest advances in ML and AI, identifying opportunities to incorporate new techniques into the competitive intelligence platform Requirements 5–10 years of professional experience in applied Machine Learning, with a proven track record of architecting and deploying high-impact models into production at global scale.

Hands‑on expertise with modern ML frameworks and tooling, such as TensorFlow or PyTorch, to drive innovation in model development. A disciplined approach to software craft, including test‑driven development, incremental delivery, and modern CI/CD deployment practices.

Exceptional programming proficiency in Python (required), with additional experience in Scala, Java, or similar languages for building robust backend systems.

Deep mastery of ML fundamentals and best practices—including feature engineering, model selection, A/B testing, and training/serving skew mitigation—alongside advanced algorithms like gradient‑boosted trees, neural networks, and transformers.

Experience leading data engineering efforts to build end-to-end ML pipelines, encompassing both high‑throughput batch processes and low‑latency real‑time systems. Strong command of architectural patterns for high-scale software applications, including the design of extensible APIs, efficient algorithms, and resilient data infrastructure.

A Bachelor’s, Master’s, or PhD in Computer Science, Machine Learning, or a closely related technical field. #J-18808-Ljbffr