Senior AI Data Engineer
Core
Building AI infrastructure and tooling to enable self-service AI applications and agentic workflows on top of Scribd's data platform.
Role type
Senior AI Data Engineer
Builds
Production-ready AI applications, agentic workflows, and self-service data interfaces for non-technical users.
Domain
Data Infrastructure / AI Engineering / LLM Systems
Deliverable
production ML models | infrastructure
Required skills
Python, SQL, Databricks (Unity Catalog, Databricks Apps), Apache Airflow, Spark, Terraform, AWS, NLP/LLM system integration, RAG pipelines, agent frameworks, data governance, secret management, encryption.
Preferred skills
Metrics-as-code frameworks, semantic layer tooling, AI model evaluation harnesses, systems thinking.
Technologies
Python, SQL, Databricks, Apache Airflow, Spark, Terraform, AWS
Responsibilities
Own deployment path for Databricks Apps; Build AI layer on Medallion Architecture; Build AI skills and agents on existing tooling; Partner with teams to identify AI tools; Embed AI tools into engineering workflow; Establish guardrails for AI-generated code; Define data modeling patterns for AI use cases; Mentor engineers on AI data engineering.
Seniority
Senior, hands-on IC