AI Engineer – Trust & Explainability (AI Platform)
Core
Building the trust and explainability layer for a multi-agent AI runtime, including tracing, evaluation, and explanation capabilities for credit union and lender customers.
Role type
Senior IC AI Engineer (LLM Observability & Explainability)
Builds
Tracing infrastructure, evaluation harnesses, and customer-facing explanation primitives for multi-agent workflows.
Domain
Fintech (Credit Unions/Lending) + LLM Systems
Deliverable
production ML models
Required skills
LLM-based systems, multi-agent workflow tracing, open-source observability frameworks, adversarial testing, evaluation metrics (LLM-as-judge), tenant isolation
Preferred skills
Experience with regulated lending contexts, red-teaming LLM applications, CI/CD integration for model evaluation
Technologies
Open-source LLM observability and tracing frameworks
Responsibilities
Build tracing across gateway, orchestration, and tool layers for multi-agent workflows; develop developer-facing trace views and human-readable explanations; integrate and extend open-source observability frameworks; build automated evaluation and safety test suites; partner with product teams on customer-facing explanation primitives.
Seniority
Senior, hands-on IC