Senior AI Engineer

Stack

Responsibilities

• ▹Lead the design and development of LLM-powered applications (chatbots, copilots, agents, internal tools)
• ▹Own and evolve the LLM evaluation strategy, including gold-standard datasets, automated eval pipelines, and scoring systems
• ▹Define metrics for factuality, grounding, robustness, and user impact
• ▹Diagnose and resolve failure modes such as hallucinations, retrieval issues, and agent breakdowns
• ▹Optimize systems for latency, cost, scalability, and reliability in production
• ▹Mentor junior engineers and guide best practices in LLM development and evaluation
• ▹Collaborate cross-functionally with product, data, and leadership to shape AI strategy
• ▹Set standards for responsible AI, including safety, bias mitigation, and observability

Requirements

• ▹5+ years of experience in software engineering, machine learning, and applied AI
• ▹Strong software engineering fundamentals (testing, modular design, dependency injection) in Python
• ▹Track record of taking AI and LLM-powered features from concept to long-term production maintenance
• ▹Experience implementing automated testing strategies for non-deterministic systems
• ▹Strong understanding of prompt engineering, RAG architectures, and LLM limitations and failure patterns
• ▹Solid experience with SQL and data analytics/visualization to inform product decisions
• ▹Strong tech leadership and mentorship skills
• ▹Clear communication of trade-offs, risks, and system performance to stakeholders

Nice to have

• ▹Experience driving ambiguous projects to completion and mentoring teams
• ▹Ability to design robust, production-grade evaluation at scale using advanced metrics
• ▹Deep expertise in model fine-tuning, adversarial red-teaming, and safety testing

Soft skills

About the company

Lodgify is a fast-growing scale-up leading the vacation rental industry, backed by $30M in funding, with 380+ employees representing over 60 nationalities, headquartered in Barcelona.