[Hiring] Founding AI Platform Engineer @Zipdev

Role Description

Our client is looking for a Senior AI Platform Engineer to build and own the core platform powering its enterprise AI products. This role focuses on identifying common patterns across client 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.

Qualifications

• 5–10 years of professional experience as a software, backend, machine learning, or applied AI engineer.
• Proven experience building and shipping AI-centric systems used by real users in production.
• Demonstrated experience designing and building a platform or major system end to end.
• Experience owning the quality of production LLM systems, including building evaluation frameworks and implementing guardrails.
• Strong experience building APIs, backend services, and data pipelines.
• Experience designing and deploying production systems in cloud environments.
• Ability to work with complex, unstructured data and design reliable systems for extraction, retrieval, and information management.
• Comfortable handling sensitive enterprise data and making engineering decisions that balance accuracy, security, cost, and latency.

Technologies & Tools

• 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.