Senior Member of Technical Staff

Harper•San Francisco, CA

19d•Onsite

About The Position

The Problem 36 million businesses in America need insurance—it’s not optional. 77% are underinsured. 40% have no coverage at all. The distribution system failed them: too slow, too opaque, too confusing. Over 90% of commercial insurance is still human-led. We’re building the inverse: 90%+ AI-led, pushing toward the higher 90s. Not by patching legacy workflows—by building AI that makes humans more effective, improves the customer experience, and eliminates friction at every step. We’re adding ~1,000 customers per month. We’ve grown 100x since last year. We’re looking to do even more this year—and that’s why we’re hiring. You’ll be one of the most senior engineers at Harper. That means you own systems end-to-end. The Thesis The difference between MTS and Senior MTS: you own outcomes, not tasks. You look at a business problem—“we need to 10x our quoting capacity”—and figure out what to build, build it, and make sure it works. You architect systems AND implement them. You mentor by building alongside people, not by reviewing PRs from a distance. The Role This isn’t a “tech lead who attends meetings” role. You make architectural decisions that stick, and ship code that directly generates revenue. No waiting for consensus—we don’t have time for consensus.

Requirements

3-6 years software engineering experience
Production experience with LLM applications and AI systems
Strong architectural skills with hands-on implementation
Track record of owning systems end-to-end
Based in San Francisco or willing to relocate

Nice To Haves

Voice AI or real-time systems experience
Experience building agent frameworks or evaluation systems
Prior startup experience

Responsibilities

Own core AI infrastructure — LLM orchestration, prompt management, retrieval systems, structured output parsing
Design agent architecture — Define abstractions that let us ship new agents in days
Build evaluation that works — Systems that measure whether agents are getting better at closing deals
Architect decision trace capture — Make every AI judgment traceable
Own platform scale — Thousands of concurrent conversations, sub-second response times