🛠 Tech Stack

💼 About This Role

You'll lead the design and deployment of LLM-powered applications and own the evaluation strategy for production-grade generative AI systems. You'll optimize performance, mentor engineers, and shape AI strategy.

🎯 What You'll Do

• Design and develop LLM-powered applications (chatbots, copilots, agents, internal tools)
• Define evaluation strategy with datasets, benchmarks, and automated pipelines
• Diagnose and resolve hallucinations, retrieval issues, and agent breakdowns
• Optimize systems for latency, cost, scalability, and reliability
• Mentor junior engineers and guide LLM best practices

📋 Requirements

• 5+ years in software engineering, ML, and applied AI
• Strong Python fundamentals (testing, modular design, dependency injection)
• Experience deploying LLM-powered features from concept to production
• Deep understanding of RAG architectures and retrieval evaluation

✨ Nice to Have

• Experience with model fine-tuning and adversarial red-teaming
• Designing production-grade evaluation at scale with advanced metrics

🎁 Benefits & Perks

• 🌍 Remote-first culture with headquarters in Barcelona
• 🚀 Fast-growing scale-up backed by $30M funding
• 🧑‍🤝‍🧑 Diverse team of 380+ people from 60+ nationalities
• 📈 Impactful role shaping AI strategy