Forward Deployed Engineer, HTS Assist

About the jobThe Forward Deployed Engineer plays a pivotal role in deploying, customizing, and optimizing Hopper’s HTS Assist, our agentic AI voice and chat assistant for travel. This role ensures the HTS Assist delivers seamless automated service experiences across partners.As a Forward Deployed Engineer, you’ll combine engineering depth with customer-facing collaboration. You’ll embed directly with partners to design, implement, and iterate on AI-driven service automation, from API integration across telephony, CRM, travel supply systems and orchestration to LLM prompt design, testing, and ongoing optimization, while providing data-driven insights and testing support to continuously improve performance and reliability.This role bridges applied AI engineering, field deployment, and partner co-creation, helping Hopper scale the next generation of autonomous service technology for the travel industry. It also plays a key part in Hopper’s broader mission to scale the HTS Assist ecosystem; ensuring reliable, responsible, and partner-centric AI automation at every stage of deployment.Key Responsibilities Assist Platform OperationsConfigure and maintain HTS Assist deployments across partner environments, including conversational flows, LLM prompt management, and system orchestration.Conduct user acceptance testing (UAT) and regression QA for voice/chat bots, measuring and tracking accuracy, latency, and overall conversational quality.Monitor operational health through analytics and logging tools; identify issues and coordinate fixes with Product and Core Engineering.Contribute to design of self-serve configuration capabilities for partners as HTS Assist evolves.Partner Integration & EnablementSupport both technical and operational enablement and onboarding for new partner integrations, including telephony (e.g., Twilio, Amazon Connect, Genesys, Five9, Avaya), CRM/ticketing systems (Salesforce, Zendesk, ServiceNow) and travel inventory platforms (PMS, GDS, CRS, etc.)Work hands-on with partner engineers to implement and validate HTS Assist capabilities and best practices.Maintain strong relationships with both external and internal stakeholders to ensure satisfaction, adoption, and continuous improvement of deployed solutions.Data, Quality & Continuous ImprovementDefine and track Assist performance metrics including conversation accuracy, escalation frequency, latency, and adherence to partner policies.Design experiments and analyze conversation data to improve HTS Assist outcomes, leveraging SQL, Python, and other data tools to identify trends and performance gaps.Partner with Engineering to define, implement and refine quality metrics for HTS Assist, including accuracy, escalation rate, and response effectiveness.Contribute to prompt engineering and test new conversational behaviors to ensure the assistant meets partner brand tone and customer expectations.System Architecture & Workflow AutomationUnderstand and document how telephony, CRM, and AI components interconnect; proactively identify risks or opportunities for workflow optimization.Build and maintain automation scripts and deployed tools to streamline implementation and monitoring processes.Ensure robust data governance, version control, and documentation for all integrations and configurations.Cross-Functional CollaborationServe as an operational liaison between Product, AI Engineering and operational teams to align product enhancements with operational needs.Act as an incident manager when outages or performance issues arise, ensuring swift triage, communication, and resolution.Support roadmap planning with data-backed insights into feature adoption, partner feedback, and operational pain points.Minimal QualificationsTechnical ProficiencyHands-on experience with APIs, JSON, SQL, and Python for data manipulation, workflow validation, and automation using frameworks such as Postman or Airflow.Understanding of LLM-based systems, prompt design, and conversational AI testing ... (truncated, view full listing at source)