Forward Deployed Engineer

Cozmo AI; New York (NY); On-site; USD 90,000 - 150,000; Full time

Job summary

Cozmo AI in New York is seeking engineers to join a hands-on team building AI-powered claims workflows. You will operate in a hostile data environment and design agents that run production-grade operations across field and back-office systems.

You will spend time in customer operations and in code, delivering end-to-end solutions with tight Go-Live schedules and high impact. Relocation to NYC may be required.

Qualifications

• Exceptional CS fundamentals from a top program or equivalent self-tunded proof.
• 0 to 4 years of experience; new grads welcome if demonstrated ability.
• Strong in Python or TypeScript, able to ship solo to production.
• Hands-on LLM engineering with agent systems and evals.

Responsibilities

• Deploy into enterprise claims operations and own outcomes end to end.
• Build production agent systems and the glue between LLMs and legacy software.
• Reverse engineer legacy claims applications and make them programmable.
• Design data pipelines generating hundreds of structured data points per claim.

Skills

Python

TypeScript

LLM engineering

Production systems

First-principles reasoning

Ambition evidence

Job description

About Cozmo

Cozmo is the AI operating system for property claims. When a pipe bursts in someone's home at 2am, our agents answer the call, capture the loss, enter the claim into Xactimate and Cotality, dispatch the right contractor against SLA, chase acceptances before breach and draft the carrier-ready estimate from field photos. We run both halves of a claims operation: everything the customer touches and everything that happens behind the desk.

Our customers are restoration franchisors, TPAs and adjusting firms whose boards have told them to become AI-native and who have no way to do it themselves. Our anchor is one of the largest restoration franchisors in the US.

The role

A claim is a hostile engineering environment. The data lives in Xactimate files, carrier portals, Zendesk queues, voicemails and photos of wet drywall. The workflows were designed twenty years ago and enforced by franchise agreements. SLAs are measured in minutes and breaches cost real money. Your job is to walk into that environment, reason from first principles about what the system should be, then build agents that run it in production.

You will spend part of your time inside customer operations, part of it writing code that becomes the platform. The distance between "I saw a dispatcher waste an hour on this" and "an agent now does it" should be days, and you own the whole distance.

You report to the CTO and work directly with both founders.

What you'll do

• Deploy into enterprise claims operations and own technical outcomes end to end
• Build production agent systems: prompt architectures, tool use, routing, evals, fallbacks, the glue between LLMs and systems that were never meant to have APIs
• Reverse engineer legacy claims software and make it programmable
• Design the data layer as you go. Every claim we touch generates hundreds of structured data points, and the pipelines you build become the moat
• Ship during live go-lives with hard dates and executives watching, including hurricane season surges where volume triples overnight
• Convert field solutions into platform primitives so each deployment is faster than the last

What we look for

• Exceptional CS fundamentals from a top program, or the self-taught equivalent with proof. We care about the caliber of your thinking and we will test it directly
• 0 to 4 years of experience. New grads welcome if your work says more than your resume
• You build fast and deep: strong in Python or TypeScript, comfortable across the stack, able to go from empty repo to production system alone
• Hands-on LLM engineering: you have built agent systems, written evals and know where models break, beyond calling an API in a notebook
• First-principles reasoning. When the standard workflow is wrong you notice, and you can defend the redesign to the person who has run it for twenty years
• Evidence of ambition we can inspect: research, a startup, open source, competition results, something shipped that people use
• You want to be around customers. The best FDEs treat the deployment as the interesting part

Nice to have

• Voice AI, telephony or real-time systems
• Insurance, claims or field services domain exposure
• Winning record in competitive programming, olympiads or research

How we work

We work almost six days a week, in person in New York, and go-live weeks take the seventh day too. We say this plainly because intensity is our structural advantage against incumbents with a hundred times our headcount, and because the engineers we want read this section and relax. This is the environment where nobody tells you to slow down.

Compensation

Competitive salary plus founding-level equity, weighted toward equity because we want owners, plus relocation to NYC if required.