LocationSan Francisco / Mountain View, CA or remote
Work modehybrid
Typefull-time
SeniorityLead
Experience4+ yrs
DepartmentEngineering
EquityIncluded
Company size11–50 people
First seenOct 4, 2026 · 1w ago
Verified live14h ago
At a glanceSummarised by Seekless from the posting.
Must have10
4+ years of software engineering, with experience at an AI product company, AI lab, or consumer product company
Hands-on experience building production agents with tool use, memory, and long-running conversations
Experience designing evals a team trusts to make ship decisions
Experience building on third-party APIs, OAuth, or payments
Experience building tools for LLM agents such as function calling, MCP servers, or browser automation
A record of shipping features end to end and owning the outcome
Full stack: TypeScript, React, and Next.js for the product and evals, and Postgres on the back end
Strong product and design judgment
Fluency with AI-assisted development workflows, grounded in the fundamentals to verify, correct, and own everything you ship
You want founding-team scope
Nice to have1
Post-training or fine-tuning experience is a plus
Skills
TypeScript
React
Next.js
PostgreSQL
OAuth
MCP
browser automation
Benefits
401(k)
Health insurance
Equity
All roles
About the company
Hey 👋, we’re Haz and Wyatt, the founders of Pally.
Pally is a personal assistant that lives in your texts. You text it like a friend. It replies to the messages you’ve been avoiding, books the dinner, chases the invoice, and handles the hundred small things that pile up in a week.
Read our philosophy of work →
We’re a small team based in the Bay Area, and we’re hiring people who will make Pally the #1 consumer agent in the world.
About the role
The role
You’ll own the agent and the experience. Most of Pally is a text thread. There are few buttons and no spinners. Every product decision comes out of the model as a sentence, and every sentence has to be right, fast, and able to get something done. You’ll own all of it, from how the agent decides what to do, to the tools it uses, to how the reply reads on a phone.
Responsibilities
This is a hands-on engineering role with a lot of product ownership. You’ll be in the agent code, the prompts, the evals, the integrations, and the product surfaces, talking to users and shipping to them every week. In practice that means:
•
The agent. Design and build how Pally decides to act, ask, wait, or reach out first: the tool-calling loop, memory and context assembly, prompts, and model routing so small, fast models take most turns and frontier models take the ones that matter.
•
Evaluations. Build the harness that turns “did that reply feel right?” into a number: turn-level judges, replay of real conversations, regression suites that run before every deploy.
•
The experience. How Pally reads on a phone, from the first reply to a follow-up weeks later. Onboarding, group chats, the trusted Pally network, approvals, and the web app. The first five minutes decide whether someone texts Pally again.
•
Product features. Own features end to end, from idea to the moment a user texts us that they love it. Run experiments behind feature flags, keep what works, and delete what doesn’t.
•
Integrations. Email, calendar, bookings, payments, and browser sessions for sites with no API. Tools the model calls correctly and recovers from, OAuth that works over a text message, and approval flows so Pally never spends money people didn’t agree to.
•
Talking to users. Read transcripts every day, talk to users every week, and study the numbers. What you learn decides what you build next.
We’ll measure you on one thing: how much better Pally gets at being someone’s assistant, week over week, in the evals and in how many people text it every week.
Requirements
Profile
This is a senior to staff level role. We’re looking for someone who has shipped AI products people use every day, at a frontier AI lab, an AI product company, or a team operating at that level.
•
4+ years of software engineering, with experience at an AI product company, AI lab, or consumer product company.
•
Hands-on experience building production agents with tool use, memory, and long-running conversations, and designing evals a team trusts to make ship decisions. Post-training or fine-tuning experience is a plus.
•
Experience building on third-party APIs, OAuth, or payments, and building tools for LLM agents such as function calling, MCP servers, or browser automation.
•
A record of shipping features end to end and owning the outcome, not only the ticket: you can point to a metric that moved because of something you built.
•
Full stack: TypeScript, React, and Next.js for the product and evals, and Postgres on the back end.
•
Strong product and design judgment. You notice when a word is wrong, a reply is too slow, or a flow has one step too many, and you fix it.
•
Fluency with AI-assisted development workflows, grounded in the fundamentals to verify, correct, and own everything you ship.
•
You want founding-team scope. You’ll set the bar for how Pally works and help hire the engineers who join after you.
Benefits
Practical stuff
$200–300k base + significant equity, 401(k), and health insurance. Full-time, in person in San Francisco, CA.
We work exceptionally hard. If work isn’t your primary focus, this isn’t for you. However, we also give you full autonomy over your schedule. We don’t care when you work hard, only that you do.
Hiring process
If this sounds like you, apply below. Tell us how you see the future of personal AI and why you’re excited to work at Pally.