AI Agent Product Manager, Builder

Hello Patient•Austin, TX

About The Position

Hello Patient is hiring a hands-on AI Agent Product Manager to build and improve AI voice agents from scratch. The role focuses on designing how agents listen, interpret, respond, and guide patients through healthcare workflows, turning complex requirements into natural, reliable conversations. The work includes creating prompts, conversation flows, and agent configurations, then using simulations and real conversations to identify and fix breakdowns. The Product Manager partners closely with Engineering and Customer Delivery Product Managers to ensure agent experiences perform reliably in production. The role owns agent architecture and configuration, including prompts, intents, conversation flows, tool calls, extensions, transfer protocols, and retrieval-augmented knowledge bases. It also leads technical discovery to translate customer processes, rules, exceptions, and handoffs into agent behavior; supports integrations and end-to-end testing; and helps assess technical feasibility, effort, and tradeoffs. The Product Manager is accountable for agent quality and production performance, creating evaluations, tags, and simulations; reviewing results; peer-reviewing agents; and diagnosing issues during soft launches and after go-live. The role also guides agents after handoff by authoring a QA Agent Playbook, preparing Agent Technician and QA teams, maintaining architectural ownership, reviewing pull requests, leading deeper refactors, and developing reusable components and patterns across deployments.

Requirements

At least 1 year of experience in conversational design, voice user experience, or a closely related field, with hands-on experience building AI agents or conversational systems from scratch.
Experience working closely with voice AI agents, including designing, testing, and refining their behavior in real conversations.
Strong understanding of conversation structure, turn-taking, intent recognition, ambiguity, clarification, and recovery when interactions go off track.
Hands-on prompt engineering skills and the ability to translate customer workflows into agent instructions, conversation flows, and decision logic.
Ability to review calls and transcripts, identify patterns in conversational failures, and turn findings into concrete improvements.
Technical fluency with agent-building platforms, tool calls, APIs, and integrations, including understanding how system constraints affect conversation design.
Strong ownership and ability to work across customer-facing and engineering teams in a fast-moving environment.

Nice To Haves

Background in linguistics, computational linguistics, discourse analysis, human-computer interaction, or a related discipline.
Experience shipping voice AI agents into production and improving them using real call data.
Familiarity with speech recognition and text-to-speech systems, including the effects of latency, interruptions, pronunciation, and speech recognition errors on the experience.
Experience building evaluations and simulations for conversational quality and task completion.
Background in healthcare or other environments with complex, sensitive customer interactions.
A portfolio of voice or conversational experiences built, with examples of how testing informed design decisions.

Responsibilities

Own agent architecture and configuration, including prompts, intents, conversation flows, tool calls, extensions, transfer protocols, and retrieval-augmented knowledge bases.
Lead technical discovery to translate customer business processes, rules, exceptions, and handoffs into agent behavior.
Build agents for complex healthcare workflows involving scheduling logic, patient context, EHR data, and practice-specific requirements.
Partner with Engineering on integrations, new features, and end-to-end testing, translating integration constraints into agent design decisions.
Assess technical feasibility and help the Customer Delivery Product Manager understand implementation effort and tradeoffs before scope and timelines are committed.
Author evaluations, tags, and simulation scenarios that test expected behavior, edge cases, and failure modes.
Build and run simulation suites, review results, and own internal agent quality before customer demos and testing.
Peer-review other builders’ agents and take accountability for technical approvals.
Diagnose issues during soft launch and the initial period after go-live using live conversations, evaluations, and customer feedback.
Determine whether issues need targeted fixes or agent re-architecture.
Author the QA Agent Playbook and prepare Agent Technician and QA teams to support agents after handoff.
Remain the architectural owner of agents built and advise on changes that affect their structure and behavior.
Review Agent Technician pull requests and lead refactors requiring deeper architectural work.
Assess whether expansion requests can reuse existing features or require new capabilities.
Turn patterns across deployments into reusable components and patterns to accelerate future agent development.