Our mission is to build a proactive smart assistant for everyday users to bring intelligence to conversations, errands, organising and workflows, with minimal prompting.
Our product focuses on achieving high reliability for long-running workflows, persistent context, and real-world task completion.
The system must handle multi-step reasoning, interact with external tools, and remain reliable despite non-deterministic model behavior.
Our objective is to help users complete tasks daily enjoyable with over ~90%* reduced time.
RoleThis is a deeply technical, hands-on role.
Work directly with engineers on system design, evaluation, and trade-offs-defining.
You work at the intersection of user needs, model capability, and system constraints, and are responsible for turning AI potential into real, reliable behavior in a real-world application.
What You'll be DoingResearch and define end-to-end AI system requirements from capability to behavior to user impactTranslate model capabilities, data constraints, and evaluation results into clear product and system decisionsMake hard trade-offs across quality, latency, cost, reliability, and UXWork closely with ML, backend, and mobile engineers on system design, evaluation, and iterationDefine and evolve evaluation frameworks across offline metrics, online experiments, and human feedbackDrive execution with clear specs, strong judgment, and disciplined prioritizationEnsure systems ship quickly, safely, and reliably, with strong feedback loopsOwn product quality end-to-end - correctness, predictability, and user trust What You Will NeedTechnical foundationStrong grounding in computer science fundamentals, including algorithms, data structures, and system design.
Solid understanding of ML fundamentals and how modern AI systems behave in production.