Data Scientist II, ML Infrastructure
Core
Advancing science and systems behind ML measurement, feature understanding, and causal inference at scale to build durable platform capabilities.
Role type
Senior IC ML Infrastructure Scientist
Builds
Production feature importance platforms, observational causal estimation tools, large-scale proxy metric development, and centralized ML platform tooling.
Domain
Internet / Machine Learning Infrastructure
Deliverable
production ML models
Required skills
Causal inference methods, Python, PyTorch, distributed compute (Spark, Ray), workflow orchestration (Airflow, Prefect), software development best practices, ML theory fundamentals
Preferred skills
Experience with propensity scoring, IPW, TMLE, self-serve tooling design
Technologies
Airflow, WandB, Ray, PyTorch, Spark
Responsibilities
Translate research-grade DS workflows into production ML pipelines; Apply and productionize causal inference methods; Partner with ML engineers to identify tooling opportunities; Build data-driven frameworks for feature importance and content deindexing; Design centralized ML platform tooling for model creation and evaluation.
Seniority
Senior, hands-on IC
