Prompt Engineer (Healthcare)

Talkie builds AI Agents for healthcare. Our agents handle patient–clinic communication end-to-end — voice calls, web chat, and SMS — so patients get 24/7 access to care and busy practices never miss a conversation. Every month, our AI Agents handle close to a million real patient conversations across the US and Poland. Trusted by primary care, specialty practices, and hospitals.

• Hands-on LLM experience writing and iterating on prompts for production systems.
• Ability to review conversations, extract failure patterns, and turn findings into concrete, measurable improvements.
• Strong communication and collaboration skills to work across technical and non-technical teams.
• Proactive problem-spotting and proposing fixes.
• Zero-error mindset due to real patient interactions.
• Proficiency in English at C1+ level with strong written communication.
• Availability to work 12:00–20:00 CET at least 3 days a week to overlap with US Eastern Time hours.

Nice to have:

• Experience with LLM tool-use patterns, structured outputs, and API integrations.
• Familiarity with evaluation tools such as Braintrust, DeepEval, LangSmith, or custom pipelines.
• Understanding of voice AI nuances including latency, turn-taking, and TTS/ASR.
• Background in healthcare, health-tech, or regulated industries requiring accuracy and compliance.
• Genuine curiosity for new models, reading release notes, and experimenting with fresh ideas.

• Design, write, and continuously optimize prompts powering our AI Agents to make them natural, accurate, and reliable.
• Analyze real patient-agent conversations end-to-end, identifying failure patterns, edge cases, and opportunities to improve agent behavior.
• Propose and implement technical solutions around function calling, tool use, context caching, and other LLM capabilities.
• Build and run evaluation frameworks to test agent performance before and after changes with zero margin for error.
• Create clear, structured documentation and customization instructions to tailor agents to client-specific workflows.
• Stay up-to-date with rapidly evolving LLM models, techniques, and conventions.
• Work closely with the Product Manager (US market), engineering, and client teams to ensure agent quality across deployments.