AirflowJavaPythonPyTorchScikit-LearnSparkTensorflowAIArtificial IntelligenceMachine LearningMLDeep LearningLarge Language ModelsTensorFlowscikit-learnCatBoostDatabricksRepositoryMentoringPrototypingA/B Testing
About this role
Role Overview
Design, build, and ship production new machine learning models that power core product features on the Zillow app, website, and email/push notifications.
Re-architect our core home ranking and recommendation systems to support advanced neural networks and dramatically accelerate the pace of experimentation across surfaces.
Own the full lifecycle of your models, from offline experimentation and prototyping with massive datasets to online deployment, A/B testing, and performance monitoring.
Pioneer the application of cutting-edge deep learning and large language models (LLMs) to improve our home shopping experience.
Develop new AI components that optimize how we display and when we recommend homes, ensuring we connect shoppers with the right content on the right properties at the right time.
Collaborate in a cross-functional group of engineers, applied scientists, product managers, and designers to define, execute, and iterate on the team's strategic roadmap.
Contribute to the team's engineering excellence by improving our machine learning infrastructure, development standards, and shared tooling.
Act as a key technical voice, mentoring other engineers and helping to shape the long-term vision for artificial intelligence in the home shopping experience.
Requirements
3-5 years of experience in developing applications in search, personalized ranking, or recommender systems
Experience developing and deploying ML models that scale to high-traffic, latency sensitive customer-facing services (100s of millions of requests per day)
Strong programming skills in a high-level language such as Python or Java
Familiarity with common machine learning libraries like PyTorch, TensorFlow, Catboost, scikit-learn and huggingface (repository)
Expertise with large scale distributed data processing systems such as Hive, Spark, Airflow, or Databricks
Experience owning the full lifecycle of customer facing machine learning models, from offline experimentation and prototyping to online deployment, A/B testing, and performance monitoring
Tech Stack
Airflow
Java
Python
PyTorch
Scikit-Learn
Spark
Tensorflow
Benefits
equity awards based on factors such as experience, performance and location