machine learning engineer for fintech products

Описание: Pleo builds spend management solutions that make managing money seamless, empowering, and effective for finance teams and employees. The company serves more than 40,000 customers and uses unique spend data to develop AI-powered product features.

Задачи

• Build and ship AI-powered product features for Pleo’s customers, owning outcomes end-to-end for a scoped area;

• Design and build end-to-end RAG systems for specific product use cases, including chunking strategies, embedding model selection, retrieval optimisation, and quality evaluation;

• Own the full AI-product lifecycle, including prompt design, context and state management, agentic loops, output parsing, edge case handling, and safe production deployment;

• Build evaluation datasets and automated eval pipelines to assess AI feature quality before and after changes;

• Instrument AI features for production observability through logging, drift detection, quality monitoring, and alerting;

• Collaborate with Product and Design to scope AI features from first principles and co-author what gets built;

• Partner with the GenAI Platform team to identify infrastructure needs and champion adoption of platform tooling;

• Support other engineers through reviews, pairing, and pragmatic technical leadership on projects you lead;

• Familiarise yourself with the codebase, tooling, and roadmap;

• Partner with the Principal Engineer to define and own the approach to AI feature development;

• Contribute to shaping the roadmap for tooling and features developed by the GenAI Core team;

• Collaborate with Product and Data teams to ship a first feature to production.

Требования

• Proven experience shipping customer-facing AI features using LLMs beyond the prototype stage and into production systems with real users;

• Deep practical experience with RAG system design and the full retrieval pipeline, including embedding models, vector databases, chunking, hybrid search, and re-ranking;

• Experience building and operating evaluation frameworks for LLM-based systems;

• Strong Python engineering skills with production-grade, tested, and maintainable code;

• Experience building APIs and data retrieval pipelines that feed context into AI systems;

• Data intuition to reason about data quality, schema, and retrieval architecture without needing a dedicated data engineer at all times;

• Experience with agentic system patterns, including tool use, multi-step orchestration, and error handling in LLM workflows;

• Familiarity with public cloud providers such as AWS and GCP;

• Openness to contributing to a Kotlin stack when needed;

• Strong product instincts and a user-focused approach to AI feature development;

• Deep understanding of LLMOps, data retrieval, prompt and context engineering, and model evaluation in production;

• Ability to discover and define problems alongside Product and Design without fully defined specifications;

• Ability to explain AI trade-offs clearly to non-technical stakeholders;

• Not primarily focused on model research or algorithm development;

• Able to own complex technical features from design through implementation;

• English for work and applications;

• Nice to have: No additional preferred qualifications specified

Условия

• Your own Pleo card;

• Catered meals or a lunch allowance based on the local office;

• Comprehensive private healthcare, with coverage options including Vitality, Alan, or Médis depending on location;

• 25 Days of holiday plus public holidays;

• Free mental health and well-being support through MyndUp;

• Paid parental leave;

• Remote, hybrid, or in-person setup is available in listed locations;

• You must be physically based in the country of your choice with a valid right to work;

• Visa sponsorship is not available;

• The role includes a system design interview, live coding interview, Hiring Manager interview, and final leadership interview