Sr. Principal AI Systems Architect

Fivetran Fivetran · Data AI · Oakland, CA · Business Intelligence Department

Architect and build Fivetran's AI analyst system, focusing on product-quality agentic capabilities, including metadata, tool interfaces, context assembly, prompt orchestration, evaluation loops, and operational patterns for real-world workflows.

What you'd actually do

  1. Define the architecture for the analyst AI stack across prompts, tools, metadata, memory and context strategies, evaluation, and runtime safety.
  2. Build the abstractions and interfaces that allow product teams to add new agent capabilities without creating brittle prompt sprawl.
  3. Design retrieval and context strategies that give the model the right information at the right time with strong cost, latency, and quality tradeoffs.
  4. Establish evaluation loops, benchmark suites, and review processes so model behavior can be measured, debugged, and improved systematically.
  5. Partner with product, engineering, and analyst-domain experts to translate real analytical workflows into robust AI-assisted product capabilities.

Skills

Required

  • AI-enabled product systems architecture
  • LLM prompting
  • Tool use
  • Retrieval
  • Structured outputs
  • Evaluation methods
  • API design
  • Orchestration
  • System boundaries

Nice to have

  • Backend engineering
  • Product constraints
  • User workflow design

What the JD emphasized

  • Deep experience building AI-enabled product systems, not just running experiments.
  • Strong software architecture skills, especially around APIs, contracts, orchestration, and system boundaries.
  • Practical understanding of LLM prompting, tool use, retrieval, structured outputs, and evaluation methods.

Other signals

  • building product-quality analyst systems
  • reason over schema and business context
  • use tools correctly
  • recover from ambiguity
  • improve through disciplined evaluation and iteration