ppAre you looking to have an impact on the daily life of millions of entrepreneurs in France (and tomorrow in Europe)? Pennylane is a fast‑growing Fintech dedicated to making accounting and finance simpler for small and medium‑sized businesses. /p h3About Pennylane /h3 pWe aim to become the most beloved financial Operating System for French SMEs and accounting firms, and soon across Europe. In five years we have built a leading SaaS platform, raised €400 million, grew from 7 founders to 1,000 employees, and served over one million enterprises and 6,000 accounting firms. /p h3Core AI Team – Role Overview /h3 pThe Core AI team sits at the heart of our AI strategy and builds the shared foundations that power all customer‑facing AI features. As an AI Engineer you will design, implement and maintain the agentic intelligence, quality and models that our solution squads rely on. /p h3Key Responsibilities /h3 ul liBuild and maintain the agent harness – the core runtime that orchestrates LLM calls, tool use, context construction, memory and guardrails – and ensure it is reliable in production. /li liOwn the evaluation stack: design evaluation pipelines, golden datasets, LLM‑as‑judge and human‑evaluation workflows; track agent performance, regressions and failure modes, and transform production failures into systematic improvements. /li liPerform prompt and behaviour engineering and retrieval/RAG at scale, defining what "good" looks like for agents completing complex accounting workflows end to end. /li liHost and improve our own small models where appropriate: serve and fine‑tune open‑source LLMs, SFT/DPO/RL training, and document‑extraction models for performance, cost and sovereignty. /li liWork closely with Product teams and domain experts (accountants) so that fulfilling real user needs remains at the core of everything we build. /li /ul h3What you can expect /h3 pbDuring the first month: /b /p ul liLearn everything about our company, teams and vision during the first onboarding week.



/li liFamiliarise yourself with our stack and AI tooling (agent harness, evaluation tooling, model providers, MCP). Deliver a few small contributions to get a concrete taste of our tools and processes. /li liMeet future stakeholders and gain deep knowledge of our product and operations. /li /ul pbDuring the first three months: /b /p ul liTake charge of roadmap items, defining and prioritising tasks autonomously. /li liBecome comfortable with our technical stack (Python, agentic frameworks, evaluation tooling, model serving and AWS). /li liContribute to larger cross‑team projects. /li /ul pbDuring the first six months: /b /p ul liProactively contribute to the team roadmap. /li liWork with engineers and data practitioners on improving our stack, AI platform and evaluation practices. /li liShare learnings and best practices within the team. /li /ul pBeyond six months you will have opportunities to mentor new team members, assume greater accountability in project leadership, and design new processes, tools and best practices. /p h3Qualifications /h3 ul li5–8 years of experience; strong in Python and building LLM and agentic systems at scale in production. /li liHands‑on experience with prompting, tool use, context construction, RAG and managing failure, state and reliability. /li liTreat evaluation as a first‑class discipline: golden datasets, LLM‑as‑judge, human evaluation, A/B testing, and measuring agent quality, regressions and edge cases. /li liGood grasp of applied LLM/ML and AI infrastructure (model serving, vector databases, cost and latency). /li liExposure to model fine‑tuning and post‑training (SFT, DPO, RL).



/li liBalanced blend of technical, business and product skills; communicate well with non‑technical domain experts and fluent in English (French not mandatory). /li /ul h3We’re looking for someone who /h3 ul liSpeaks English (levels are assessed according to the department). /li liIs energized by an ever‑shifting work environment. /li liIs highly collaborative internally and with external stakeholders. /li liHas enough experience to prioritise business‑led actions in day‑to‑day activity. /li /ul h3Recruitment Process /h3 ul liFirst interview with Talent Acquisition Manager. /li liCase study interview (75 min). /li liPast‑project interview (60 min). /li liInterview with Tech Product leaders (60 min). /li /ul h3Benefits and Perks /h3 ul li25 paid vacation days. /li liCompetitive compensation package. /li liCompany shares. /li liHome office budget and monthly coworking allowance. /li liGym and wellness benefits through Gymlib. /li liLanguage learning via Busuu. /li liLatest Apple equipment. /li liRemote work allowed within a two‑hour time difference of CET and within Europe. /li liRegular company events such as Tech Days and an annual seminar. /li /ul pFor France residents: French contract following French regulation, additional 6–12 RTT, 5 weeks of PTO, lunch credits, health coverage and events in major cities. /p h3Legal and Diversity /h3 pRecruitment scam prevention: apply only through official channels, verify sender email domains, and never pay or provide financial information. Pennylane fully embraces diversity, equity and inclusion and provides equal employment opportunities regardless of gender, sexual orientation, origin, disabilities or any other traits. /p h3Personal Data /h3 pPennylane processes your data to manage your application and assess your suitability. If your application is unsuccessful, data may be retained for up to 2 years. You may object at any time and request deletion by writing to /p /p #J-18808-Ljbffr

📌 AI Engineer — Core AI (Madrid)
🏢 Pennylane
📍 Madrid