CareerPlan
San FranciscoFull-time2026-08-28 → 2026-11-18

Core

Own the end-to-end path from signed customer to delivered results for AI agent safety evaluations, including building one-off integrations and making final judgment calls on standard compliance.

Role type

Senior IC forward-deployed engineer (AI safety/evaluations)

Builds

One-off evaluation integrations for frontier AI agents and reusable product features

Domain

AI safety, agent security, enterprise software

Deliverable

production ML models | product features

Required skills

software engineering, API integration, debugging, customer relationship management, scoping technical work, delivering bad news, turning field learnings into reusable products

Preferred skills

founding or co-founding experience, AI evaluations or red-teaming experience, executive presence with senior stakeholders

Technologies

API integrations, authentication systems, evaluation frameworks

Responsibilities

Scope testing requirements and integrate customer agents into the evaluation system; Build custom integrations for customers not yet fitting the product; Deliver evaluation results directly to customers; Make final decisions on whether customers meet the AIUC-1 standard; Collaborate with delivery, core engineering, sales, and standards teams; Translate field observations into product improvements