Prompt Engineer (Healthcare)

Talkie sp. z o.o.

Remote · Poland, United States · Poland · Mid-level

Agentic fit score: 80/100

<h3>About us</h3>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.<h3>The Role</h3>We're looking for a Prompt Engineer to own the quality and intelligence of our AI Agents — from prompt design to production. This is a high-impact role at the intersection of language, technology, and healthcare. Your work will directly shape how hundreds of thousands of patients experience care.This is not a research role. You'll be writing, testing, and iterating prompts that run live with real patients — so rigour, empathy, and a zero-error mindset matter as much as technical skill.<h3>What You'll Do</h3><ul>

<li>Design, write, and continuously optimise prompts that power our AI Agents — making them natural, accurate, and reliable.</li>

<li>Analyse real patient–agent conversations end-to-end, identifying failure patterns, edge cases, and opportunities to improve agent behaviour.</li>

<li>Propose and implement technical solutions around function calling, tool use, context caching, and other LLM capabilities that make our agents smarter.</li>

<li>Build and run evaluation frameworks to test agent performance before and after changes — because every conversation is with a real patient and there is zero margin for error.</li>

<li>Create clear, structured documentation and customisation instructions so that agents can be tailored to each client’s specific workflows and needs.</li>

<li>Stay on top of the rapidly evolving LLM landscape — new models, techniques, and conventions — and bring the best ideas back to the team.</li>

<li>Work closely with the Product Manager (US market), engineering, and client teams to ensure agent quality across all deployments.</li>

</ul><h3>What will you achieve with us?</h3><ul>

<li>Shape the experience that hundreds of thousands of patients have when they reach out to their doctor — across every channel — and make it better every single day.</li>

<li>Push the boundaries of what LLM-powered AI agents can do in a highly regulated, real-world, multi-channel environment.</li>

<li>Build evaluation and quality systems for conversational AI that don’t exist yet — you’ll be creating the playbook.</li>

<li>Have a direct, measurable impact on patient access to healthcare in both the US.</li>

</ul><h3>Requirements</h3>This is a young and fast-moving field. We care less about years of experience and more about how you think, learn, and work.<h3>Must have</h3><ul>

<li>LLM Experience — Hands-on experience writing and iterating on prompts for production systems. More importantly, you learn fast — this field changes weekly and you keep up. </li>

<li>Analytical Rigour — Ability to review conversations, extract failure patterns, and turn findings into concrete, measurable improvements.</li>

<li>Communication & Collaboration — Comfort on client calls and working across technical and non-technical teams; you translate clearly in both directions. This is not a “sit in a cave and prompt all day” role ;). </li>

<li>Proactivity — You spot problems before being asked, flag them, and come with a proposed fix.</li>

<li>Zero-Error Mindset — Our agents talk to real patients. You understand the responsibility and bring the precision and care it demands.</li>

<li>English — C1+ English, strong written communication. Our agents talk to US patients.</li>

<li>Shifted Hours — You are available to work 12:00–20:00 CET at least 3 days per week (optimally 5) to overlap with US Eastern Time business hours.</li>

</ul><h3>Nice to have</h3><ul>

<li>Function Calling & Tool Use - Experience with LLM tool-use patterns, structured outputs, and API integrations.</li>

<li>Evaluation Frameworks- Familiarity with eval tools — Braintrust, DeepEval, LangSmith, or custom pipelines.</li>

<li>Multi-Channel Experience - Understanding of voice AI nuances: latency, turn-taking, TTS/ASR — and how they differ from chat or SMS.</li>

<li>Healthcare Background - Prior work in healthcare, health-tech, or regulated industries where accuracy and compliance are non-negotiable.</li>

<li>Genuine Curiosity - You read release notes. You experiment with new models. You show up on Monday with fresh ideas.</li>

</ul><h3>Your goals as a Prompt Engineer </h3><h3>Short term — first 3 months</h3><ul>

<li>Develop a deep understanding of our AI Agent architecture, prompt patterns, client configurations, for our US market product.</li>

<li>Audit existing agent conversations, identify the top quality issues, and implement prompt improvements with measurable impact.</li>

<li>Take ownership of the agent testing and evaluation process — establish baselines and a repeatable QA workflow.</li>

<li>Get up to speed on our tooling (Langfuse, ClickUp, internal platforms) and the team’s ways of working.</li>

</ul><h3>Longer term — first 12 months</h3><ul>

<li>Own the end-to-end prompt and agent quality lifecycle across our US deployments.</li>

<li>Build and maintain a structured evaluation framework that catches regressions before they reach patients.</li>

<li>Develop comprehensive customisation documentation that enables scalable client onboarding.</li>

<li>Become the team’s go-to expert on LLM capabilities, staying ahead of model releases and new techniques.</li>

<li>Contribute to shaping our product roadmap with insights from conversation analysis and agent performance data.</li>

</ul><h3>What we offer</h3><ul>

<li>Competitive pay with benefits: employment contract or B2B contract.</li>

<li>A role with real purpose — we’re changing how patients access healthcare in the US.</li>

<li>Flexible working arrangements — remote, office, or hybrid.</li>

<li>Work equipment — Mac laptop, monitors, keyboard, mouse, and a setup for both office and home (including a comfy chair).</li>

<li>Benefits: private medical care, Multisport card, annual offsite, training budget.</li>

<li>Unique company culture based on mutual trust, honest feedback, and autonomy.</li>

<li>Working with cutting-edge AI technology on a product that’s genuinely useful to real people.</li>

<li>A structured onboarding process to help you find your feet.</li>

</ul><h3>What are we like as a company?</h3>We are friendly, direct, and driven by curiosity and ambition. We value a growth mindset and see failure as a learning opportunity. Our culture is built on inquiry and critical thinking — asking questions is encouraged and thorough investigation is standard. We’re proactive problem-solvers who don’t shy away from challenges. When something’s broken, we acknowledge it, propose solutions, and fix it. And yes — we love to have fun too. Dancing till early hours, karaoke nights... we’ve got a long tradition of good times at Talkie!<h3>Our recruitment process</h3>Reflecting our culture, our recruitment process is respectful and collaborative. We aim to create a welcoming environment where you can be yourself and get to know us better. The entire process typically takes 2–3 weeks.<h3>What to expect</h3><ul>

<li>Initial Contact — we'll reach out by email or phone if your application is a fit.</li>

<li>First Interview (1h online) — mutual fit and getting to know each other.</li>

<li>Second Interview (1.5h online) — practical, hands-on case study/task</li>

<li>Reference Check — We’ll ask for references and verify them.</li>

<li>Offer — We’ll make an offer or share detailed feedback.</li>

</ul>Originally posted on <a href="https://himalayas.app">Himalayas</a>

Apply on the original posting