What you will do
Orchestrate Intelligence
•Architect for RAG: You’ll design and scale the pipelines for Retrieval-Augmented Generation (RAG), transforming massive volumes of unstructured IT logs and documentation into optimized Vector Embeddings.
•Scale vector infrastructure: You will be responsible for the health and performance of our vector databases (e.g., Pinecone, Milvus, or Weaviate), ensuring sub-second retrieval speeds for agentic reasoning loops.
Master Data Transformation
•Engineer semantic layers: Move beyond simple ETL to build knowledge graphs and semantic layers that provide agents with the necessary context to navigate complex infrastructure puzzles.
•Automate data excellence: Using a keen eye for detail, you’ll build automated data guardrails to detect noise, bias, or PII (Personally Identifiable Information) before it reaches the model, ensuring our AI remains safe and impactful.
Own the Backbone
•Solve meaningful challenges: Serve as the bridge between raw, messy data sources and deep technical AI work, identifying and resolving quality issues at the source.
•Progress to production: With a well-defined methodology and software engineering prowess, you will build, deploy, and maintain the CI/CD pipelines for our data infrastructure, ensuring that our context window remains fresh and reliable.