AI Engineer - Trust & Explainability

To enhance the AI platform's trust and explainability, the full-time remote AI Engineer - Trust & Explainability will develop tracing and evaluation capabilities for multi-agent workflows, ensuring transparency and reliability in AI outputs while collaborating with product teams to create user-facing explanations. Key Responsibilities

Build tracing and correlation across multi-agent workflows, ensuring readability and understanding of agent actions Develop platform primitives for customer-facing explanations, including confidence metadata and summaries of agent reliance Integrate and extend open-source observability and evaluation frameworks to meet platform needs

Required Qualifications

3+ years of professional software engineering experience with independent feature delivery in production Proficiency in Python with production experience; familiarity with TypeScript is a plus Hands-on experience with large language model integrations and related technologies Solid understanding of algorithms, data structures, and software design fundamentals Experience with distributed tracing or observability tooling in a production environment