Founding AI Engineer

Location
San Francisco, CA (HQ) — in-person most days with flexibility when you need it. Must be authorized to work in the U.S.

Company Description

At Second Nature, we are driven by a mission to help individuals live more seamlessly by designing software that intuitively understands and caters to daily needs. Our vision challenges the limitations of current technology, shifting the dynamic from one that demands user effort to one that works effortlessly for you. We strive to create a world where technology simplifies and enhances life naturally and quietly.

Our first product, Poppy , is a proactive consumer companion that lives on your iPhone. Poppy plugs into your calendar, email, music, fitness level, and many more integrations to nudge you with helpful suggestions throughout your day.

Role Description

This is a full-time, on-site Founding AI Engineer role based in San Francisco, CA. We're looking for a builder‑researcher hybrid who's shipped LLM products in production, obsesses over latency graphs, can whip up a jaw‑dropping demo in a weekend hack, and ship it to production the following week.

The Founding AI Engineer will play a key role in developing and improving the agentic AI architecture that powers Poppy. Responsibilities include building and running evals, implementing state-of-the-art agentic architectures that balance quality, cost, and latency, and solving complex pattern recognition challenges. You will work closely with the founding team to shape the company's core offerings and technological foundation.

What you'll do (First 90 days)

• Jump straight into the codebase and immediately begin improving our architecture to make Poppy more accurate and fast

• Orchestrate LLMs across our in-house context engine, aiming to achieve sub-500ms end‑to‑end latency.

• Build eval pipelines, orchestration graphs, workflows, and kick off on‑device inference pilots

Must-Haves

• Proficiency in Computer Science and Software Development

• Strong expertise in orchestrating cloud-based LLM's

• Deep intuition for latency/accuracy/cost trade‑offs.

• Experience in building and deploying Python on the web

• Ability to collaboratively design algorithms and systems

• Passion for innovative technology and crafting user-centric solutions

• Experience in a startup environment is a plus