AI Systems & Data Engineer

We're building the kind of platform we always wanted to use : fast, flexible, and built for making sense of real-world complexity. Behind the scenes is a robust, event-driven architecture that connects systems, abstracts messy workflows, and leaves room for smart automation. The surface is clean and simple. The interactions are seamless and intuitive. The machinery underneath is anything but. That’s where you come in.

We’re a well-networked founding team with strong execution roots and a clear roadmap. We’re backed, focused, and delivering fast.

We are seeking an AI Systems & Data Engineer to join our team. We are building a fast, flexible, and complex platform with a robust, event-driven architecture. This role requires expertise in building data pipelines within the Databricks environment, specifically for ingesting unstructured data, and leveraging that data to build AI agents.

💥 What You’ll Do

• Design and build data pipelines in Databricks for ingesting unstructured data.
• Construct retrieval-augmented generation (RAG) systems from scratch using ingested data.
• Build agentic LLM pipelines utilizing frameworks like LangChain, LangGraph, and LangSmith.
• Own orchestration of PySpark and Databricks workflows to prepare inputs and track outputs for AI models.
• Instrument evaluation metrics and telemetry to guide the evolution of prompt strategies.
• Work alongside product, frontend, and backend engineers to tightly integrate AI into user-facing flows.
• Leverage Databricks features such as Auto Loader for automatic detection of new files on cloud storage and schema changes.
• Utilize Delta Lake for reliability, security, and performance on the data lake for streaming and batch operations.
• Apply Databricks Workflows for orchestrating tasks to integrate data.
• Implement Delta Live Tables for building reliable data pipelines with a declarative approach.
• Python (primary language for all LLM + orchestration work)
• LangChain + LangGraph + LangSmith
• Databricks + PySpark for processing, labeling, and training context
• Postgres, and custom orchestration via MCP
• GitHub Actions, GCP

You’ll be a crucial member of rolling out products that will have immediate impact.

chaos : fixed cycles & cooldowns protect focus and keep context switching low

✅ What We’re Looking For

#J-18808-Ljbffr