AI-First Principal Engineer (Tech Lead)

About

We are building an AI-native SaaS for real estate. The product is a PropTech SaaS platform where LLMs and AI agents are not bolted on top - they are the architecture. Owners, operators and guests interact with the AI system through natural language. AI autonomously generates compliance documents, routes staff, answers guest queries from RAG-indexed knowledge base in real time and orchestrates financial split-payments.

But the product is only half of it.

We are equally an AI-first engineering organization. The way we build is as differentiated as what we build. Our daily development loop - specification, implementation, code review, testing, deployment, on-call response - should run on a custom orchestrator of coding and operations agents. Human engineers operate at the level of intent, architecture, judgment and review. Agents should do most of the typing.

The role

This is the role that defines how that system works and how we build the product.

This is a hands-on technical leadership role at the core of the company's future, with a single defining characteristic: you will architect both the product development & testing approach and the AI based engineering system that builds it.

You will own the design, construction and operation of an internal AI-first development platform - the orchestrator, the agent fleet, the specification format, the evaluation harness, the CI/CD wiring - that lets a small team of senior humans ship at the velocity and surface area of a larger conventional team. You will decide what the human engineering team does, what agents do.

You will simultaneously own the production AI layer of the product itself - RAG pipelines, agent workflows, prompt strategy, vector memory - because the same intuition that makes the engineering org work makes the product work.

You will write production code daily. You will read agent diffs daily. You will build and tune evals continuously. 

We operate in a fast-moving startup environment where speed and precision both matter. You must be opinionated about which engineering tasks AI does well today, which it does not and how to close that gap inside our codebase deliberately.

What you will own & do

AI-First Engineering System (the differentiator)

• Build and operate the AI-first engineering system: design the orchestrator (task decomposition, agent coordination, review gates, deployment/rollback) and manage a fleet of coding, review, testing, and ops agents.
• Establish a spec-driven development model: convert product intent into machine-readable specs that agents can implement, test, and evolve reliably over time.
• Define governance and trust: set clear boundaries for agent autonomy vs. human approval, implement verification layers (evals, tests, canaries, traces), and codify standards as machine-readable rules.
• Continuously optimize performance and autonomy: run evaluation frameworks (A/B tests, drift detection, cost/latency tracking), make model/infra decisions, and increase the share of SDLC handled autonomously each quarter.

Technical Architecture & Strategy

• Define and own the full technical architecture of the SaaS platform: service boundaries, API design, data models and infrastructure
• Make fast, reasoned architectural trade-offs under startup timelines without accumulating critical technical debt
• Set the technical direction for AI integration in the product: the AI layer is a core product pillar not a feature.

Hands-On Engineering

• Write production-grade code - much of it through and alongside agents, all of it to your standard (stack to be defined).
• Build and maintain frontend interfaces where needed (stack to be defined). Own database design and query performance
• Design and ship real-time systems: live dashboards, event-driven pipelines.

Product AI & LLM Layer

• Own the end-to-end AI layer of the product (from prototype to production): lead adoption of new LLM tools, build and operate RAG pipelines, manage vector databases, and ensure only production-ready solutions are used.
• Design and orchestrate AI workflows and prompt strategies to power core use cases (guest chat, operator briefings, compliance docs, natural-language commands) while continuously evaluating and integrating cutting-edge AI capabilities.

Integration Layer

• At a certain point own the full integration architecture across all third-party systems - IoT platforms, smart locks, payment rails, government and regulatory APIs.
• Ensure the integration layer is reliable, observable and extensible - future integrations include additional regulatory APIs and secondary trading infrastructure.

Engineering Leadership

• Lead a small, high-caliber hybrid team (engineers + AI agents): set technical standards, run code reviews, unblock delivery, and ensure consistent execution under pressure while maintaining high quality.
• Act as the bridge between business and engineering: translate product needs into clear, agent-executable work, build an AI-first engineering culture, and mentor the team on effectively working with AI (what to delegate vs. retain).

Infrastructure & Reliability

• Own and build scalable infrastructure from scratch: set up CI/CD with agent participation, design cost-efficient cloud architecture and ensure production readiness for live operations.
• Implement full observability and reliability practices: monitoring, alerting, agent traceability, cost/latency tracking, API health and an on-call capable system that is transparent and controllable.