Senior Member of Technical Staff

The Problem36 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 ThesisThe 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 RoleThis 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.What You’ll DoOwn core AI infrastructure — LLM orchestration, prompt management, retrieval systems, structured output parsingDesign agent architecture — Define abstractions that let us ship new agents in daysBuild evaluation that works — Systems that measure whether agents are getting better at closing dealsArchitect decision trace capture — Make every AI judgment traceableOwn platform scale — Thousands of concurrent conversations, sub-second response timesYou Might Be a Fit If…You’ve owned production systems (not contributed to—owned; you got paged when it broke)You architect AND implement—the best architecture comes from people who live with what they buildYou’ve built AI systems in production (LLM applications, agent frameworks, RAG, voice AI)You write code with AI (Cursor, Claude Code) and manage multiple sessionsYou’re 3-6 years into your careerRequirements3-6 years software engineering experienceProduction experience with LLM applications and AI systemsStrong architectural skills with hands-on implementationTrack record of owning systems end-to-endBased in San Francisco or willing to relocateNice to HaveVoice AI or real-time systems experienceExperience building agent frameworks or evaluation systemsPrior startup experienceCompensationSalary: $160,000–$230,000 + performance bonuses & equityLocation: San Francisco, in-officeBenefitsHealth, dental, and vision insuranceCommuter benefitsTeam meals and snacksThe Process15-min founder call — Alignment on mission and paceIf in SF: Super Day on-siteIf outside SF: Technical phone screen, then on-siteTo ApplyIf you want to own systems that run a real business and work with founders who will actually listen to you—send your resume and tell us about a system you’ve owned.Compensation Range: $160K - $230K