Founding AI Platform Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop and oversee the primary AI orchestration platform, encompassing document ingestion and processing to provide grounded, source-cited answers.

• Design and sustain a multi-provider LLM gateway featuring prompt caching, record-replay functions, and evaluation-gated model routing.

• Create evaluation frameworks and guardrails to assess LLM output quality, mitigate hallucinations, and ensure consistent production performance.

• Construct fact-extraction pipelines and semantic matching systems tailored for intricate commercial real estate documents, such as loan documents and rent rolls.

• Align extracted data with a commercial real estate semantic field dictionary.

• Spearhead the architecture of a multi-tenant knowledge graph and retrieval layer.

• Implement enterprise governance features, including PII detection, policy compliance checks, human escalation workflows, and cryptographic audit trails.

• Recognize reusable functionalities across client-specific implementations and integrate them into the shared platform.

• Design and develop reusable integrations with enterprise real estate platforms like DealCloud and Yardi.

• Work closely with the CEO and deployed engineers to shape product architecture and technical direction.

⛳️ Requirements

• 5–10 years of relevant professional experience as a software, backend, machine learning, or applied AI engineer.

• Demonstrated experience in creating and deploying AI-centric systems utilized by real users in production environments.

• Relevant production AI expertise involving agentic workflows, LLM pipelines, document extraction, or retrieval systems dealing with unstructured data.

• Proven track record of designing and constructing a platform or significant system from start to finish, making crucial architectural and technical choices.

• Experience in founding or early engineering positions, independently managing a service, leading a 0-to-1 build, or guiding a small engineering team.

• Practical experience in overseeing production LLM quality, including evaluation frameworks, guardrails, and strategies for measuring and preventing hallucinations or unreliable outputs.

• Strong background in building APIs, backend services, and data pipelines.

• Experience in designing and deploying production systems within cloud environments.

• Capability to work with complex, unstructured data and devise reliable systems for extraction, retrieval, and information management.

• Comfortable managing sensitive enterprise data while balancing accuracy, security, cost, and latency.

• Proficiency in Node.js and TypeScript.

• Familiarity with PostgreSQL.

• Experience with AWS.

• Knowledge of LLMs, agentic workflows, RAG, document extraction, evaluation frameworks, and semantic search.

• Experience with knowledge graphs, data pipelines, and multi-tenant systems.

• Familiarity with enterprise APIs and third-party software connectors.

• Nice to have: experience in an early-stage startup, ideally from seed to Series B, as an early or founding engineer.

• Nice to have: experience with LLM gateways, document AI, knowledge graphs, or advanced retrieval systems.

• Nice to have: experience in fine-tuning or computer vision.

• Nice to have: familiarity with financial or commercial real estate documents.

• Nice to have: experience integrating with DealCloud or Yardi.

• Nice to have: experience in forward-deployed engineering environments.

• Based in or around Chicago (preferred).

🏝️ Benefits

• Competitive salary and equity options.

• Comprehensive health, dental, and vision insurance.

• Flexible working hours and remote work opportunities.

• Professional development and training programs.

• Collaborative and innovative work environment.