Quick Summary
NOTE: This is a FULLY remote role. Candidates must be physically based within EMEA to ensure effective collaboration with the team, peers, and internal customers.
Hostaway is an industry-leading, AI-powered vacation rental management platform, trusted by over 20,000 property managers globally. Designed for professional short-term rental operators, Hostaway streamlines operations for greater efficiency and accelerated growth. We are a profitable, high-growth company and the first short-term rental Property Management System unicorn. Join us during this exciting growth phase!
About the Role: Staff Backend Engineer, AI Platform
We are building Hostaway's AI Platform, the foundational infrastructure powering every AI-driven feature across our product. This is a dedicated platform team focused on creating an agentic framework that enables all Hostaway engineering teams to ship reliable, production-grade AI capabilities.
As a Staff Backend Engineer, you will own the architecture and technical direction of this critical platform. Your responsibilities include leading the design and implementation of a multi-agent system, encompassing an agent orchestrator, LLM gateway, prompt and tool versioning, an evaluation framework, and end-to-end observability. Your work will directly impact Hostaway's ability to deliver AI-powered experiences to over 50,000 property managers and their guests.
This is a high-autonomy, high-impact position, reporting directly to engineering leadership. You will collaborate closely with product, design, and engineering teams company-wide. You will take ownership of a well-defined architecture and strong technical foundation, evolving and scaling it as the platform matures and adoption grows.
What You’ll Do
- Own the AI Platform architecture and lead the technical vision for the multi-agent system, including the agent delegator, sub-agents, config service, LLM gateway, evaluation framework, conversation history, and observability stack.
- Build production-grade AI infrastructure, designing and implementing core services for reliable, versioned, observable, and safe AI feature deployment at scale.
- Drive the evaluation and quality strategy, establishing quality gates, prompt comparison workflows, hallucination detection, and CI/CD integration for measurable confidence in AI features.
- Shape the LLM gateway strategy, ensuring centralized provider failover, model routing, cost tracking, and rate limiting to prevent duplicated efforts.
- Champion cross-team adoption, collaborating with product teams to make the AI Platform easy to integrate. Publish internal blueprints and define integration patterns.
- Influence engineering-wide practices, driving best practices for prompt engineering, tool design, observability, and agent testing.
- Mentor and elevate engineers, raising the technical bar across the AI team through code review, architectural guidance, and hands-on pairing.
Required Skills & Experience
- 8+ years of software engineering experience, with at least 2 years at a Staff or equivalent level.
- Deep Python expertise, with proficiency in writing production-grade Python services.
- Production experience with LLM-based systems, including building, shipping, and operating AI features or platforms at scale. Understanding of operational realities: prompt versioning, evaluation, cost management, observability, and failure modes.
- Strong architectural instincts to design scalable systems and make pragmatic trade-offs.
- Familiarity with the modern AI tooling ecosystem (e.g., PydanticAI, LangChain, LangGraph, LiteLLM, Langfuse, Phoenix, MLflow).
- Multi-agent architecture experience is a strong plus (agent orchestration, tool calling, structured output, context management).
- Comfort working across a polyglot stack (Python, Go, PHP, React frontend).
- Infrastructure fluency with AWS, Kubernetes, CI/CD pipelines, and operating services in production.
- Proven ability to influence cross-team adoption of platforms, patterns, or standards.
What Success Looks Like
- The AI Platform becomes the trusted foundation for all AI features at Hostaway.
- Prompt changes are versioned, tested, and deployed with rigorous standards.
- Production AI features are observable, cost-tracked, and recoverable, with rapid issue detection.
- You become the go-to technical authority for applied AI at Hostaway, sought out by other engineering teams.
- The platform scales effectively to support a broader agent ecosystem without fundamental rearchitecture.