AI Product Architect In Office (Austin, TX)

About the Role We're looking for an AI Product Engineer who can bridge the gap between cutting-edge AI capabilities and real healthcare needs. You'll spend 40%+ of your time crafting and optimizing prompts while driving product strategy, testing new AI features, and translating complex client requirements into lean, launchable solutions. As our platform grows, you'll be the first to test multi-agent architectures, evaluate new models, and identify which AI innovations actually move the needle for patient outcomes. You're equally comfortable running A/B tests on conversation flows and scoping down a client's ambitious bot idea into something we can ship next week. What You'll Do Core Prompt Engineering & AI Implementation (40%+) Design and optimize prompts for complex healthcare workflows including multi-agent systems, appointment scheduling, and patient engagement flows Collaborate with engineering to implement and test new AI architectures, models, and conversational AI features Run experiments comparing different models, prompt strategies, and conversation approaches Build prompt evaluation frameworks and testing pipelines that scale across multiple healthcare use cases Product Strategy & Client Requirements Translate ambitious client requirements into lean MVPs that can be launched and iterated quickly Create product hypotheses and validation frameworks for new AI features and healthcare use cases Scope complex multi-agent workflows into phases that minimize risk while maximizing learning Partner with clients to identify the core problem beneath their feature requests Platform Testing & Quality Assurance Serve as primary user of our internal AI agent platform, stress-testing new features and identifying improvement opportunities Design and execute end-to-end testing for new AI capabilities, model deployments, and platform releases Create testing scenarios that cover edge cases, failure modes, and integration points Establish metrics and monitoring systems for conversation quality, model performance, and user satisfaction Technical Product Management Work closely with engineering team to prioritize AI/ML platform features and improvements Identify opportunities to leverage new AI technologies (advanced prompting techniques, RAG improvements, model fine-tuning) Drive roadmap decisions based on client feedback, platform usage data, and emerging AI capabilities Communicate technical AI concepts to non-technical stakeholders and clients What You Bring Required Experience 3-5 years in product management, AI/ML engineering, or technical product roles Advanced experience with LLMs, prompt engineering, and AI model evaluation Track record of taking products from concept to launch, preferably in fast-paced environments Experience with lean startup methodologies, hypothesis-driven development, and MVP scoping Strong analytical skills with ability to design experiments and interpret results Technical Requirements Hands-on experience with AI/ML frameworks, APIs, and model comparison Understanding of conversational AI architecture, multi-agent systems, and prompt optimization techniques Ability to work with engineering teams on technical implementation and system design Experience with A/B testing, metrics analysis, and data-driven product decisions Preferred Qualifications Background in healthcare technology or regulated industries Experience with AI safety, model alignment, or responsible AI practices Familiarity with software development processes and platform architecture Previous experience as a power user or early adopter of AI tools and platforms Growth Opportunities You'll develop deep frontlines understanding of conversational AI architecture, multi-agent systems, and prompt optimization techniques. This goes beyond hackathons and GitHub repos to agents that work in the real world on hundreds of real patients. You'll get front-row access to cutting-edge LLM failure modes that few people globally get to observe—understanding why agents break in production and building systems that consistently work for real healthcare interactions. Location & Team Austin, TX Work closely with the GM, Agent Platform and Product who somehow convinced therapists to teach her about patient communication (they're probably regretting it). Obsessed with measuring whether AI can actually be funny AND helpful. Builds modular systems because apparently even empathy needs to scale. As the primary user of our platform, you'll have direct influence on engineering priorities and product direction without needing formal authority We're building AI that actually works in the messy reality of healthcare. If you love turning AI possibilities into practical solutions, let's talk. #J-18808-Ljbffr S27a