Founding Software Engineer

$4.5 trillion flows through the US mortgage market every year, and almost every dollar of it is still processed by hand. We're here to change that.

Copperlane is building the AI employee for mortgage origination. Behind every mortgage is a person's full financial story: income, debts, savings, life circumstances. Our AI loan officer assistant, Penny, reads that story, translates it into accurate risk assessments, verifies documents, and clears conditions in real time. She does the work that buries loan officers in paperwork so they can do what they got into this industry to do: help people buy homes.

Mortgage is the most important financial product in most Americans' lives. We believe AI should make it faster, cheaper, and more human. Our co-founders bring family roots across Freddie Mac, Fannie Mae, and FHFA, combined with engineering backgrounds from quant finance, Princeton, and multiple startups. We're a small, effectual team in San Francisco, and we're just getting started.

We're looking for a founding software engineer (member of technical staff) who is obsessed with building agentic AI systems and wants to ship real product from day one. You'll work across the stack but spend most of your time on backend systems, building and orchestrating AI agents that interact with borrowers, loan officers, and third-party platforms in a regulated industry.

This is not a "learn on the job quietly" role. You'll be in the room with customers, see how your code impacts their workflow, and iterate fast. This role is on-site in our San Francisco, CA office.

1. Designing and building agentic AI pipelines: tool use, multi-step orchestration, evaluation, and reliability at scale
2. Backend services in Python (FastAPI) on Aurora PostgreSQL and AWS
3. Multi-tenant architecture with strong security and compliance boundaries
4. Integrations with mortgage industry platforms (LOS systems, voice, messaging)
5. Frontend experiences in React, Vite, and TanStack when the product calls for it

1. Strong fundamentals in backend engineering (Python preferred)
2. Hands-on experience building with LLMs: agent loops, tool calling, prompt engineering, evals
3. Comfort with PostgreSQL, schema design, and migrations
4. Exposure to multi-tenancy patterns, auth, or compliance-aware systems is a plus
5. Bonus: sharp design sensibility and strong frontend skills (React, Vite, TanStack). We value engineers who care deeply about craft on both sides of the stack.
6. High energy, low ego, genuine curiosity about how things work
7. You care about the people using what you build

Stack: Python/FastAPI, React/Vite, DynamoDB, EKS, S3.

Architecture: Penny is an autonomous agent that reasons over a borrower's full financial context, decides what to do, and does it: pulling documents, verifying data, clearing conditions, reaching out to borrowers over voice, SMS, email, or chat. A channel adapter pattern lets her operate across different Points-of-Sale, Teams/Slack, web, and voice through a single agentic core.

Hard problems we're solving:

• Agentic orchestration: planning, tool use, and multi-step reasoning over messy, unstructured mortgage data
• Long-term memory: Penny maintains context across interactions spanning days or weeks per borrower, not just single sessions
• Balancing creativity and determinism: giving an LLM enough flexibility to handle the unpredictable reality of borrower situations while staying accurate and compliant in a regulated financial domain
• Deep integrations with legacy System-of-record platforms
• Real-time voice AI for autonomous borrower communication

If you want to build autonomous AI systems in a domain where correctness actually matters, this is the place.

We run a quick interview process. You can expect 1-2 calls with the founders, 1 technical interview, then 1 work trial onsite in SF.