Франция
Германия
ИспанияStaff Software Engineer, AI Agents (Python)
1 нед. назад
ФранцияГерманияИспания+1LeadRemote
python
Build production systems integrating AI to support Anti-Financial Crime teams at .
Требования
- Production AI experience: You have shipped an AI agent or agentic workflow used by real users and can explain its orchestration, tool use, state, structured outputs, evaluation, retries, and failure modes
- Strong backend engineering: You bring solid system-design fundamentals across architecture, APIs, databases, integrations, reliability, observability, maintainability, and scalability
- Staff-level autonomy and judgement: You make sound decisions independently, communicate trade-offs clearly, and know when to optimise for speed and when quality is non-negotiable
- Product and stakeholder thinking: You can turn ambiguous operational pain into a valuable solution, challenge assumptions, prioritise scope, and define success without relying on a PM
- End-to-end ownership: You are willing to discover, build, ship, operate, maintain, and continuously improve the systems you create
- Learning agility: You are curious about AFC and regulated workflows and can ramp up quickly in a complex domain; prior fintech or compliance experience is helpful, not required
- Pragmatic technology choices: Python experience and familiarity with current model providers or agent frameworks are useful, but transferable production principles matter more than expertise in a specific language or vendor
- [DIVERSITY] At , we understand that true diversity isn’t just about ticking boxes on a hiring checklist. Apply regardless of the boxes you tick - who knows? You may have the missing piece of the puzzle we’ve been searching for all along.
- [HIRING PROCESS DURATION] On average, our hiring process lasts 20 working days. More information on our candidate journey here
- [DATA RETENTION] By applying, you agree that processes your personal data to assess your application. Your data is kept for up to 2 years in our candidate pool. Read our Privacy Notice for full details.
Другое
- [OUR MISSION AND CUSTOMERS] We are creating the freedom for SMEs to succeed by delivering Europe's leading finance workspace with banking at its core, augmented by financial tools. We are proud to be rated 4.7 on Trustpilot, based on 60,000 reviews. Our culture puts customer satisfaction at the core of what we do (more about our culture here ).
- [OUR JOURNEY] Founded in 2016 and launched in 2017 by Alexandre and Steve , has grown to 1,700 Qontoers serving over 750,000 customers across 8 European countries. We have been profitable since 2023, and we are just getting started.
- [OUR BELIEFS] We hire for skills and potential. With 80+ nationalities, 45% women, of which 56% of women in our leadership team, diversity isn't a program; It's who we are. We've built a discrimination-free hiring process because the best teams are built on merit.
- [AI AT ] AI is deeply embedded in how we work ( here ) - Every Qontoer gets unlimited access to the best AI tools. We want people who experiment without waiting for permission, push AI beyond the obvious, know when to trust it, and when to question it.
- Location: France, Germany, Spain, or Italy — remote within these hiring locations.
- Join us as a Staff Applied AI Engineer, Backend to build production systems in which AI is a core runtime capability. You'll help 's Anti-Financial Crime teams investigate cases faster and with greater confidence by turning complex operational workflows into dependable, measurable tools.
- Build production AI systems: Design and ship agentic tools and AI-powered workflows that gather context from multiple internal systems, orchestrate models and tools, parse structured outputs, and handle uncertainty and failure safely
- Own projects end to end: Lead discovery with AFC stakeholders, shape the solution, make architectural decisions, implement and launch it, then operate, maintain, and improve it in production
- Design robust backend foundations: Build reliable, maintainable, and extensible services, APIs, databases, and integrations around evolving AI models and tooling
- Make AI behaviour measurable: Define evaluation approaches, observability, fallbacks, and human-review mechanisms; monitor output quality, acceptance and edit rates, throughput, and operational impact
- Deliver measurable operational value: Reduce investigation lead time and expand automation across AFC workflows through pragmatic, incremental delivery
- Shape the team’s technical direction: Lead design discussions, anticipate risks, balance speed with quality, and help raise the team’s capability in production agentic systems
- AI at the heart of the system: This is not a conventional backend role using AI only as a coding assistant, nor an ML research role. You’ll build real products where model behaviour, orchestration, evaluation, and failure handling are production concerns
- High autonomy: There is no dedicated Product Manager. Engineers work directly with AFC stakeholders and own the path from an ambiguous operational need to a measurable production outcome
- Lean, iterative delivery: The team uses a daily 15-minute blocker sync, bi-weekly 1:1s, and lightweight tracking, leaving engineers focused on building and solving problems
- A close user feedback loop: You’ll collaborate directly with operational teams and measure success through investigation lead-time reduction, output quality, human acceptance and edit rates, adoption, throughput, and resources saved
- A complex, meaningful domain: You’ll learn how to build safe, scalable AI automation in a regulated environment where reliability and auditability matter
- You’ll join ’s AI Compliance Tooling team within the Financial Crime Compliance domain. The current team brings together Ioannis, the Tech Lead and a hands-on contributor; Staff Backend Engineer Enrique; Staff Machine Learning Engineer Luca; and Senior Backend Engineers Izan and Robson. The team is growing with two additional staff-level hybrid backend/AI hires.
- One important clarification: the team does not build fraud-detection engines or KYC/KYB rule engines. It consumes upstream signals and builds the AI-powered automation and intelligence layer used by human investigators. One current system gathers information from 10–15 internal tools and produces a structured compliance analysis for a person to approve or edit, reducing treatment time from approximately 15–20 minutes to about 30 seconds.