AI Engineer

At Pylon, we're a small team building a very ambitious product in the mortgage space.

At this early stage, we're looking for engineers who see the opportunity to apply LLMs thoughtfully not as an end in itself, but as a tool to reduce complexity, improve decisions, and deliver meaningful automation.

We're in search of people who love working at the intersection of algorithms, data, and software engineering and who are excited to ship LLM-enabled systems as part of a deeply technical product team.

You:

• You're a strong traditional engineer first. You have a solid foundation in software engineering and computer science fundamentals. You care about system design, code quality, and building things that work reliably at scale.

• Write clean, maintainable code. This is a production engineering team. We need code that other engineers can understand, modify, and trust—especially when dealing with the inherent unpredictability of LLMs.

• Love hard problems. Complex solution spaces excite you. Maybe that means orchestrating multiple LLMs, applying optimization techniques, or recognizing when a rules engine is actually the best answer.

• Are rigorous about impact. When you build something, you care whether it correctly models and solves the core domain problem. You're excited to dig deep into mortgage domain algebra and build the right abstractions. You choose the right tool for each problem—sometimes that's an LLM, sometimes it's a simple heuristic.

• Are comfortable in unfamiliar domains. Mortgage expertise isn't required. What matters is your eagerness to learn the constraints and nuances that make solutions actually work in practice.

• Have gotten your hands dirty with LLMs. You've experimented with LLMs—maybe through personal projects, hackathons, or just tinkering on weekends. You understand the basics of prompt engineering, context management, and the development cycle. This role is your chance to apply that curiosity at production scale.

• Are genuinely excited about language models. You've been following the space, reading papers or blog posts, trying out new models and techniques. You understand their potential and limitations. Professional LLM experience isn't required—we're looking for informed enthusiasm and hands-on curiosity.

What we're not:

Building a CRUD app:
We're building a platform that's only possible due to deep technology investments and thinking hard from first principles. Cargo-culting what's come before won't be sufficient.
If you're looking to do mostly plumbing / lego piece assembling, Pylon may be very frustrating for you

An LLM wrapper:
Mortgage is a sprawling mess of problems, and there isn't one tool that solves every one of them. We use LLMs, but we've reached for tools in multiple disciplines like mixed-integer linear optimization and programming language research.

An easy job:
We're building a lot of things from the ground up for the first time. Working at Pylon is like a research project where you have to ship to intelligent, opinionated customers regularly.
It's basically guaranteed you'll be handed a task that is too difficult for you to do. You might fail sometimes. You might have no idea where to start. Our team leans heavily on each other, but there's no getting around the difficulties.

What we are:

A small team:
We don't have an army of engineers. If you find something is broken, you are probably the best one to fix it.

All the code we write has to punch above its weight in maintainability and toil reduction. If you have a good idea, you have much more ability to put it into action than at a large company.

We need generalists: Specialization is for big companies that already have everything figured out. If you're smart, flexible and like getting into everything, we want you.

Working in a regulated space: Mortgage is regulated both federally and at the state level.
We move fast, but breaking things isn't an option.

Job title: LLM Engineer
Stock options: Own a piece of the company and we all win together
Benefits: Health insurance, 401K, dental, etc.

Our technology stack:
We don't require prior experience in all of these—just an eagerness to learn and strong fundamentals:

• TypeScript across frontend and backend

• PostgreSQL

• GraphQL

• NestJS

• Nx build system

• Sagittarius

• AWS CDK + ECS

In this role, you'll:

• Design and implement LLM-powered features that improve automation, decisioning, or user experience

• Build robust workflows and agent strategies with effective context management

• Work across the stack to integrate LLMs into production systems with clean interfaces

• Prototype and evaluate new LLM techniques and approaches when they solve real customer problems

• Partner with engineers, PMs, and domain experts to turn fuzzy product ideas into scalable systems

• Maintain a healthy skepticism and bias toward simplicity, knowing when LLMs are the right choice and when they aren't

The $13 trillion mortgage industry at the core of the American economy runs on broken assembly lines with human-powered workflows, stitched-together software, and a series of capital markets intermediates. The costs to originate are at an all time high despite foundational shifts in technology.

Pylon is rewiring mortgages from the ground up. We are building the only API-first, programmatic infrastructure that fully automates credit, compliance, capital, and operations. For the first time, originators can build and scale mortgage businesses entirely through software, not people. Our team comes from Stripe, Better, and Affirm, and we are backed by Conversion Capital, QED, Citi, Fifth Wall, Peter Thiel, and the founders of Ramp, Mercury, Blend, and others.