Quick Summary
NOTE: This is a FULLY remote role, requiring the candidate to be based within EMEA for effective collaboration with teams, peers, and internal customers. While not restricted to a specific country or city, applicants must be physically located within EMEA.
Trusted by over 20,000 property managers globally, Hostaway stands as an industry-leading, AI-powered vacation rental management platform. Designed for professional short-term rental operators, Hostaway centralizes operations for enhanced efficiency and accelerated growth.
As a profitable, high-growth company and the first short-term rental Property Management System (PMS) unicorn, we invite you to join us during this exciting expansion phase. Learn more about our recent valuation and story here.
About the Role: Staff Backend Engineer, AI Platform
We are building Hostaway's cutting-edge AI Platform, the foundational infrastructure powering every AI-driven feature across our product suite. This is a platform engineering role focused on constructing an agentic framework that empowers all Hostaway engineering teams to deploy reliable, production-grade AI capabilities.
As a Staff Engineer, you will own the architecture and technical direction of this critical AI platform. Your leadership will guide the design and implementation of a sophisticated multi-agent system, encompassing an agent orchestrator, LLM gateway, prompt and tool versioning, a robust evaluation framework, and comprehensive end-to-end observability. Your contributions will directly impact Hostaway's ability to deliver AI-powered experiences to over 50,000 property managers and their guests.
This high-autonomy, high-impact position reports directly to engineering leadership. You will collaborate closely with product, design, and engineering teams company-wide. Inheriting a well-defined architecture and strong technical foundation, your role is to take ownership, evolve the platform, and scale it as adoption and maturity grow.
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 to ensure AI features are reliable, versioned, observable, and safely deployable at scale.
- Drive the evaluation and quality strategy, establishing quality gates, prompt comparison workflows, hallucination detection, and CI/CD integration to ensure every AI feature ships with measurable confidence.
- Shape the LLM gateway strategy, centralizing provider failover, model routing, cost tracking, and rate limiting to eliminate duplicated effort across teams.
- Champion cross-team adoption by collaborating with product teams across Hostaway to make the AI Platform easily accessible. Publish internal blueprints, define integration patterns, and enable teams to build specialized agents without requiring deep platform knowledge.
- Influence engineering-wide best practices for prompt engineering, tool design, observability, and agent testing across the organization.
- Mentor and elevate engineers, raising the technical bar within the AI team and beyond through code review, architectural guidance, and hands-on pairing.
Required Skills & Experience:
- 8+ years of software engineering experience, with at least 2 years operating at a Staff or equivalent level.
- Deep Python expertise: highly proficient and opinionated about writing production-grade Python services, as the AI platform is built in Python.
- Production experience with LLM-based systems: proven ability to build, ship, and operate AI features or platforms serving real users at scale, understanding operational realities such as prompt versioning, evaluation, cost management, observability, and failure modes.
- Strong architectural instincts: capable of designing systems that start simple and evolve gracefully, knowing when to consolidate components and when to extract, and making pragmatic trade-offs between speed and extensibility.
- Familiarity with the modern AI tooling ecosystem: experience with frameworks and libraries like PydanticAI, LangChain, LangGraph, LiteLLM, Langfuse, Phoenix, MLflow, or comparable tools, with the ability to evaluate and integrate them confidently.
- Multi-agent architecture experience is a strong plus: experience designing systems with agent orchestration, tool calling, structured output, and context management.
- Comfort working across a polyglot stack: while the AI Platform is Python-based, Hostaway's product includes Go services, a PHP monolith, and a React frontend; curiosity and adaptability to understand and integrate with code across these technologies are essential.
- Infrastructure fluency: comfortable with AWS, Kubernetes, CI/CD pipelines, and operating services in production environments.
- Cross-team influence: demonstrated ability to lead through clarity and credibility, successfully driving adoption of platforms, patterns, or standards beyond your immediate team.
What Success Looks Like:
- The AI Platform becomes the trusted foundation for every AI feature at Hostaway, with teams building on it by default.
- Prompt changes are versioned, tested, and deployed with the same rigor as code releases.
- AI features in production are observable, cost-tracked, and recoverable, ensuring rapid issue detection and resolution.
- Other engineering teams actively seek your guidance on building AI capabilities, establishing you as the go-to technical authority for applied AI at Hostaway.
- The platform scales effectively from current use cases to a broader agent ecosystem without requiring fundamental rearchitecture.