Member of Technical Staff – Product Engineering

Hone•San Francisco, CA

17h•Onsite

About The Position

Hone is building agentic AI systems, called engines, that pursue goals over weeks and months, maintain their own agents and code, involve people when judgment is needed, and improve from corrections. As a Member of Technical Staff in Product Engineering, you will own the product surfaces people use to set up, supervise, and calibrate engines, end to end from schema to user interface. You will build interaction patterns for persistent, multiplayer AI systems, including onboarding, real-time activity, review and approvals, routines, memory, permissions, and integrations with the tools people already use. The role is based in San Francisco and is in person Sunday through Friday. Hone offers competitive salary and meaningful equity, health and dental insurance, maternity and parental support, relocation support, and visa sponsorship.

Requirements

At least 2 years of engineering experience, or equivalent depth through open-source work or personal projects.
Experience at a fast-growing startup.
Experience building products from scratch and shipping them to real users.
Experience owning polished features end to end, from backend to user interface.
Strong product and design judgment, including knowing what to cut, what to polish, and when to ship.
Strong full-stack fundamentals, including Python, TypeScript, React, Postgres, real-time interfaces, and debugging unfamiliar code.
Use coding agents every day while understanding every line of code you ship.
Build and tinker for fun and care about how products are made and used.

Nice To Haves

Founded a company or shipped agent products.
Work at the intersection of design and engineering, prototyping in code and paying close attention to spacing, motion, and copy.

Responsibilities

Build engine creation, onboarding, and calibration experiences, from the user's first goal through production.
Create interfaces that make long-running agent swarms understandable, showing what they are doing, why, and what they plan to try next.
Build task inbox, approvals, and review experiences, including feedback loops that turn corrections into lasting changes in engine behavior.
Develop frontier interfaces and generative UI that let engines create custom interfaces for eliciting user feedback and judgment in context.
Build multiplayer interactions around persistent engines, including shared and personal memory, conflicting feedback, and per-person permissions.
Develop engine experiences in chat and email.