Murphy AI is a next-generation debt collection platform powered by artificial intelligence, designed to optimize recovery rates while maintaining respectful and personalized communication. Our advanced automation streamlines the process of collecting overdue invoices for businesses, providing a seamless and effective solution.

Our platform integrates effortlessly with ERP systems or supports CSV uploads to ensure smooth access to data on unpaid invoices. Using AI-driven agents, we engage with debtors across multiple channels, including SMS, email, phone calls, and more. For cases where payment arrangements are unsuccessful, we facilitate escalation to legal proceedings through trusted partnerships with law firms.

As a fast-growing startup that has already made an impact within just a few months in the market, we are building a talented team to scale our operations and drive our vision forward. Join us in redefining debt recovery with innovation and empathy.

Type: Full-time, Hybrid in Barcelona

💼 About the Role

As a Prompting Engineer at Murphy, your mission is to design, evaluate, and iterate the business-facing prompts that power our AI agents’ conversations with users across channels like voice, SMS, and email.

This role goes beyond writing: you’ll own the full prompt evaluation pipeline, including:

• The design and maintenance of counter agents to test prompt performance before going live.
• The use of LLMs as judges to assess quality, tone, and outcome alignment.
• The creation of evaluators to continuously monitor real interactions and flag issues.

You will play a key role in shaping Murphy’s messaging strategy and directly impacting our Success Rate, the core metric that drives our business.

📝 Responsibilities

• Prompt Design & Iteration: Write and refine business-layer prompts across all communication channels.
• Prompt Analysis: Measure how each prompt variation impacts success rate, engagement, and user behavior and then optimize accordingly.
• Continuous Improvement: Review real conversations weekly and iterate based on evidence.
• Prompt Validation Pipeline:
  • Design and run counter-agent simulations to test prompts pre-launch.
  • Apply LLM-as-a-judge frameworks to evaluate clarity, empathy, and accuracy.
  • Build and deploy **evaluators** to monitor production conversations and detect regressions.
    

• Experimentation: Launch A/B or multivariate tests to evaluate tone, flow, and logic.
• Cross-Functional Collaboration:
  • With AI Engineers to understand prompt behavior at execution.
  • With Product to ensure alignment with user journeys.
  • With Data to define and monitor prompt KPIs.
    

📚 Requirements

• Experience: 2+ years working with prompts, LLMs, conversational UX, or evaluation of AI outputs and Data Analytics.
• Data Orientation: Confident using prompt-level KPIs and conversation data to drive structured improvement.
• Initiative: Strong ownership mindset—you fix things before being told.
• Writing Skills: Clear, concise, and strategic writing tailored to drive real business outcomes.
• Hands-On Python Experience: Able to write clean, efficient code to test prompts, simulate agent behavior, and automate QA workflows.
• Business-Driven Thinking: You understand how messaging impacts recovery, conversion, and user trust—and you design with that in mind.
  

⭐️ Nice to have

• Familiarity with tools like ElevenLabs, LangFuse, OpenAI, or other LLM frameworks.
• Experience with voice-based agents.
• Background in UX writing, linguistics, or computational language.
• Exposure to regulated industries such as finance, collections or insurance.
  

🤝 What we offer

💰 Salary: €35.000 – €45.000 gross/year

📈 Stock options: Because we all build Murphy together – you'll own a piece of what we’re creating.

🧩 Impact: Be part of our startup journey from day one, playing a key role in our growth and building something meaningful from the ground up.

📚 Learning: Continuous development through trainings, knowledge-sharing, and exposure to other top-tier startups in our ecosystem.

🍱 Healthy meals: No more boring tupperware – enjoy daily meals with Nora Foods. We cover 50% of each order!

🚴‍♂️ Ride into work: Forget traffic jams – hop on your Panot e-bike and cruise to the office! We cover 50% of your subscription.

🛜 Hybrid & Flexible: Our default setup is hybrid – 3 days a week at our office in Poblenou, surrounded by a thriving tech scene, and 2 days of remote work. But if there’s one thing that defines us, it’s flexibility: we trust you to organize your time and space in the way that helps you do your best work.

📚 Our Process

We believe that hiring is a two-way street: while we get to know you, you also deserve the chance to understand who we are, how we work, and what makes Murphy AI special. Here’s what you can expect:

1️⃣ First Interview – Getting to Know You
A conversation with a future teammate who’s excited to find a new colleague. We’ll talk about your story, what drives you, and what you’re looking for next—no trick questions, just a genuine exchange.

2️⃣ Second Interview – Deep Dive
You’ll meet the Hiring Manager and potentially another team member. This is a more technical discussion where we explore your skills in detail, walk through real scenarios, and answer any questions you might have about the role.

3️⃣ Tech Assessment or Business Case
A practical exercise to see how you approach challenges similar to those you’d tackle at Murphy. You’ll have time to reflect and showcase your thinking—no rush, no surprises.

4️⃣ Coffee at the Office with the Founders
Finally, you’ll join us in our Barcelona office for a relaxed coffee with the founders and the Hiring Manager. It’s the perfect opportunity to experience our culture firsthand and meet more of the team who could soon be your colleagues.

👉 To learn more about how we hire and what to expect at every step, feel free to explore our Hiring Guide! 

👉 We are committed to building a diverse, inclusive, and equitable workplace where everyone, regardless of background, identity, or experience, feels valued and empowered to thrive. We believe that different perspectives drive innovation and success, and we actively foster an environment where all voices are heard and respected.