Skip to content

Open nowPosted 5 hours ago

Founding AI Platform Engineer

Zipdev

Where
United States
Work mode
Remote
Get the CV for this job

From $25 per CV, paid once. No subscription.

Your applicationOpen nowFounding AI Platform EngineerZipdev · United States
  1. YouYes, apply to this one.

  2. CV RocketCV written for this posting.

  3. 25 readersRecruiter, hiring manager, skeptic. Round after round.

  4. CV RocketApplied on Zipdev's own form.

The reply lands in your private mailbox

3×more interviews than doing it yourself with ChatGPT.

The clock on this job

Early applications get read.

13.7% of postings close within 7 days. Measured by our own scanner across the market.

Share of postings closed within
  1. 2.2%1 day
  2. 4.7%3 days
  3. 13.7%7 days
  4. 22.1%14 days
  5. 37.8%30 days
  6. 59.1%60 days
This job: posted 5 hours ago

The posting

Our client is a seed-stage enterprise AI company building an AI platform specifically for the commercial real estate industry. Its platform transforms a firm's documents and data into a structured knowledge graph that AI agents can reason over, helping investors, owners, operators, and developers automate workflows and access reliable answers backed by source citations.

The company combines a recurring platform subscription with forward-deployed engineers who build custom workflows within client environments. Its vision is to become the foundational AI platform for the commercial real estate industry, bringing agentic workflows, transparency, and governance to a traditionally underserved market.

Backed by a real-estate-focused venture fund with strong industry relationships, the company already works with established commercial real estate firms. This is an opportunity to join a small, five-person team, work directly with the CEO, and take founding-level ownership of a product with significant growth potential.

About the Role

Our client is looking for a Senior AI Platform Engineer to build and own the core platform powering its enterprise AI products. While forward-deployed engineers focus on developing custom applications for individual clients, this role focuses on identifying common patterns across those engagements and turning them into reusable platform capabilities.

This is a highly technical, hands-on engineering position with significant architectural ownership. You will work closely with the CEO and engineering team to build the AI orchestration layer, LLM infrastructure, document intelligence pipelines, and knowledge graph that power reliable AI workflows across commercial real estate clients.

Key Responsibilities

  • Build and own the core AI orchestration platform, from document ingestion and processing to grounded, source-cited answers.
  • Design and maintain a multi-provider LLM gateway with prompt caching, record-replay capabilities, and evaluation-gated model routing to optimize cost, quality, and latency.
  • Develop evaluation frameworks and guardrails to measure LLM output quality, prevent hallucinations, and ensure reliable production performance.
  • Build fact-extraction pipelines and semantic matching systems for complex commercial real estate documents, including loan documents and rent rolls.
  • Map extracted information to a commercial real estate semantic field dictionary to improve consistency, accuracy, and data reliability.
  • Lead the architecture of a multi-tenant knowledge graph and retrieval layer.
  • Implement enterprise governance capabilities, including PII detection, policy checks, human escalation workflows, and cryptographic audit trails.
  • Identify reusable functionality across client-specific implementations and incorporate it into the shared platform.
  • Design and build reusable integrations with enterprise real estate platforms such as DealCloud and Yardi.
  • Collaborate directly with the CEO and forward-deployed engineers to influence product architecture and technical direction.

Requirements

  • Experience: 5–10 years of professional experience as a software, backend, machine learning, or applied AI engineer.
  • Production AI Experience: Proven experience building and shipping AI-centric systems used by real users in production. Relevant experience includes agentic workflows, LLM pipelines, document extraction, or retrieval systems over unstructured data.
  • Architectural Ownership: Demonstrated experience designing and building a platform or major system end to end, making key architectural and technical decisions. This could include founding or early engineering roles, owning a service independently, leading a 0-to-1 build, or leading a small engineering team.
  • LLM Evaluation & Reliability: Experience owning the quality of production LLM systems, including building evaluation frameworks, implementing guardrails, and measuring and preventing hallucinations or unreliable outputs. Hands-on experience with evaluations is required.
  • Backend Engineering: Strong experience building APIs, backend services, and data pipelines.
  • Cloud Infrastructure: Experience designing and deploying production systems in cloud environments.
  • Data & Systems Thinking: Ability to work with complex, unstructured data and design reliable systems for extraction, retrieval, and information management.
  • Enterprise Readiness: Comfortable handling sensitive enterprise data and making engineering decisions that balance accuracy, security, cost, and latency.

Technologies & Tools

The ideal candidate will have experience with some of the following:

  • Backend: Node.js, TypeScript
  • Database: PostgreSQL
  • Cloud: AWS
  • AI/ML: LLMs, agentic workflows, RAG, document extraction, evaluation frameworks, semantic search
  • Data Architecture: Knowledge graphs, data pipelines, multi-tenant systems
  • Integrations: Enterprise APIs and third-party software connectors

Nice to Have

  • Experience working at an early-stage startup, ideally seed to Series B, as an early or founding engineer.
  • Experience with LLM gateways, document AI, knowledge graphs, or advanced retrieval systems.
  • Fine-tuning or computer vision experience.
  • Familiarity with financial or commercial real estate documents, such as loan agreements, rent rolls, and investment materials.
  • Experience integrating with commercial real estate platforms such as DealCloud or Yardi.
  • Experience in forward-deployed engineering environments, particularly companies that combine a shared platform with custom client implementations.
  • Based in or near Chicago.

What Success Looks Like

  • A reliable AI platform that supports multiple enterprise clients and their workflows.
  • Production LLM systems with measurable quality, strong evaluations, and effective hallucination prevention.
  • Reusable platform capabilities developed from patterns identified across client engagements.
  • Efficient model routing that balances output quality, cost, and latency.
  • A scalable knowledge graph and retrieval architecture designed for complex commercial real estate data.
  • Strong governance, security, and auditability across enterprise workflows.
From $25, paid onceGet the CV for this job

What happens when you press

One press. We do the rest.

  1. A CV for this posting

    Written against Zipdev's own wording, from every piece of relevant proof in your profile.

  2. 25 readers review it

    Recruiter, hiring manager, skeptic and more read every draft, round after round. You get the best round.

    The review screen in CV Rocket: how each CV was read, round by round.
  3. We apply on Zipdev's form

    Our application engine gets through the hardest forms there are. Where a question needs you, AI suggests the best answer. Don't want us applying from our IP addresses? Use our Chrome extension: we apply straight from your own browser.

    An application in CV Rocket: every answer filled in on the employer's form.
  4. Every reply, sorted

    Zipdev's answer lands in your private mailbox, and we classify it on arrival: interview, question, rejection.

    The CV Rocket inbox: each employer reply classified as an interview, an action or a rejection.
  5. Reply with AI

    AI helps you write the email, checks it and sends it. We show you whether the recruiter read it.

  6. The interview in your calendar

    Full integration with your calendar. The invitation goes straight in.

    An interview invitation in the CV Rocket inbox, added to the candidate's calendar.
Get the CV for this job

From $25 per CV, paid once. No subscription.

Why it works

3×

more interviews than doing it yourself with ChatGPT.

ChatGPT writes a CV and never learns what happened to it. We see every reply. For each CV we know:

  • How it was written, and how the review scored it
  • When we applied, and how long after the posting went up
  • Which posting, which company, which city
  • Who got the interview, and who heard nothing

That is how we know which CVs get called.

Get the CV for this job

From $25 per CV, paid once. No subscription.

The numbers game

More applications. More interviews.

Every application goes out with its own CV, written for that posting and paid once. Send enough of them and the law of large numbers finds you the job.

By hand5–10
With CV Rocket100
applications a day

Before you press

Straight answers

Get the CV for this job

From $25 per CV, paid once. No subscription.

What if my background isn't good enough?

We make the most of the background you have. The CV uses every piece of relevant proof your profile holds, and one of the 25 readers reads your whole profile and flags what the CV left out.

Do you really apply for me?

Yes, on the employer's own form, the hardest ones included. Where a question needs you, you answer it right there and AI suggests the best answer. Don't want us applying from our IP addresses? Use our Chrome extension: we apply straight from your own browser.

Is it a subscription?

No. You pay once per CV, from $25. Every application goes out with its own CV, written for that posting.

One job. One CV.
Paid once.

Pick the posting you want. We write for it, apply for you and catch the reply.

Get the CV for this job

From $25 per CV, paid once. No subscription.