About the Role
๐ช๐ต๐ฎ๐ ๐ ๐ฎ๐ธ๐ฒ๐ ๐๐น๐ผ๐๐ฑ๐ฏ๐ฒ๐ฑ๐ ๐จ๐ป๐ถ๐พ๐๐ฒAt Cloudbeds, we're not just building software, we're transforming hospitality. Our platform powers hotels across 150 countries, processing billions in bookings annually. From boutique properties to large hotel groups, we help hoteliers transform operations and uplevel their commercial strategy through a unified platform that integrates with hundreds of partners. And we do it with a completely remote team. Imagine working alongside global innovators to build AI-powered solutions that solve hoteliers' biggest challenges. Since our founding in 2012, we've continually been recognized for excellence, most recently earning top honors at the 2026 HotelTechAwards for Best Hotel Management Software and landing on Deloitte's Technology Fast 500 again, but we're just getting started. ย ๐๐ผ๐ ๐ฌ๐ผ๐'๐น๐น ๐ ๐ฎ๐ธ๐ฒ ๐ฎ๐ป ๐๐บ๐ฝ๐ฎ๐ฐ๐:As a ๐ฆ๐ฒ๐ป๐ถ๐ผ๐ฟ ๐ฆ๐ผ๐ณ๐๐๐ฎ๐ฟ๐ฒ ๐๐ป๐ด๐ถ๐ป๐ฒ๐ฒ๐ฟ on the Core AI Squad, you'll design, build, and operate customer-facing AI platform capabilities that power intelligent product experiences across Cloudbeds. This is a product engineering role focused on production AI systems, agentic workflows, evaluation, and observability - not an internal tooling role. You'll work primarily in Python while collaborating across our broader PHP and Java ecosystem, building systems where correctness, reliability, latency, cost, and model quality are core to the job. Your goal is to help Cloudbeds ship AI-powered customer experiences that are useful, trusted, scalable, and measurable.ย ๐ข๐๐ฟ ๐๐ผ๐ฟ๐ฒ ๐๐ ๐ฆ๐พ๐๐ฎ๐ฑ:The Core AI Squad owns the customer-facing AI platform infrastructure, agentic workflows, and evaluation and observability foundations that enable AI-powered experiences across Cloudbeds products. The team builds the production capabilities that let us evaluate models and providers for specific use cases, orchestrate tools and workflows, measure quality over time, and integrate AI safely into real customer journeys. You'll join a senior, product-minded group that values ownership, pragmatic architecture, fast learning, and strong collaboration across product, design, data, and engineering.ย ๐ช๐ต๐ฎ๐ ๐ฌ๐ผ๐ ๐๐ฟ๐ถ๐ป๐ด ๐๐ผ ๐๐ต๐ฒ ๐ง๐ฒ๐ฎ๐บ:
โข Design, build, and operate customer-facing AI platform services and product features primarily in Python, while integrating with PHP and Java systems as needed
โข Build and evolve agentic harnesses, including agent runtimes, workflow orchestration, tool execution, state management, recovery paths, and evaluation hooks
โข Integrate agents and LLM-powered workflows into production systems with strong attention to reliability, correctness, latency, scalability, and cost
โข Evaluate models and providers for specific product use cases, using clear success criteria and abstractions that keep the platform flexible as the AI ecosystem evolves
โข Own evaluation, tracing, observability, and quality feedback loops for AI features so the team can detect regressions, understand behavior, and improve over time
โข Write clean, well-tested, well-documented code and advocate for engineering best practices, test automation, maintainability, and operational excellence
โข Collaborate with product, design, data, security, and engineering partners to turn ambiguous AI product opportunities into reliable customer-facing features
โข Comfort building, debugging, and operating services that interact with PostgreSQL, SQS, gRPC, and REST APIs, including data models, event streams, service contracts, and versioning
โข Contribute as a senior individual contributor through technical leadership, architecture input, pair programming, code reviews, and mentorshipย ๐ช๐ต๐ฎ๐ ๐ฆ๐ฒ๐๐ ๐ฌ๐ผ๐ ๐จ๐ฝ ๐ณ๐ผ๐ฟ ๐ฆ๐๐ฐ๐ฐ๐ฒ๐๐:
โข 5+ years of software engineering experience building, shipping, and operating production systems
โข Strong proficiency with Python in production environments, including APIs, services, tests, debugging, and operational ownership
โข Hands-on experience building, integrating, or evaluating agentic systems, agent harnesses, tool orchestration, or LLM-powered workflows
โข Experience with agentic frameworks and tooling such as LangChain, LangSmith, LangGraph, or similar platforms (PydanticAI, CrewAI, etc)
โข Experience with MCP, vector databases, retrieval patterns, RAG architectures, or AI evaluation platforms
โข Comfortable working across a polyglot stack, especially contributing to or integrating with PHP and Java services when the product requires it
โข Familiarity with prompt and version management, guardrails, tracing, LLM observability, cost and latency optimization, or human-in-the-loop workflows
โข Experience with cloud infrastructure and containerization such as Docker, Kubernetes, and AWS, plus experience working with remote-first, globally distributed teams
โข Experience with API-driven design, distributed systems, data modeling, and reliable service boundaries
โข Strong knowledge of software best practices, design patterns, performance, se