ai engineer for spend management products

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 develops products for the future of business spending.

• Build and ship multiple AI-powered product features across agentic workflows, spend intelligence, automated actions, and other areas;
• Advise Product, Design, Engineering, and business stakeholders and prioritise valuable product opportunities;
• Discover and define products rather than only implementing specifications;
• Own the evaluation, monitoring, and operationalisation of AI features in production;
• Set up evaluations, track drift and performance, and manage prompt changes safely;
• Establish how AI feature operations are handled at scale and own production development;
• Act as a design partner to the GenAI Core platform team;
• Challenge platform decisions with evidence from real feature delivery;
• Define clear requirements and validate platform choices in production;
• Establish and enforce practical standards for AI feature delivery in product squads;
• Apply evaluation strategies, monitoring expectations, safe prompt and versioning practices, and privacy and safety guardrails using GenAI Platform tooling;
• Upskill the team through mentorship, reviews, pairing, and lightweight playbooks;
• Familiarise yourself with the codebase, tooling, and roadmap;
• Partner with the Principal Engineer to define and own the approach to AI feature development;
• Shape 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.

• Proven experience shipping multiple GenAI features into production at scale in a customer-facing product;
• Experience shipping multi-step, tool-using agents in a user-facing product;
• Ability to autonomously scope, design, and build scalable AI solutions from complex business challenges and product visions;
• Strong judgment regarding evaluation, retrieval quality, tool use, failure modes, and product value;
• Experience applying evaluation and observability to LLM systems, including tests, golden sets, online metrics, and monitoring;
• Strong understanding of privacy and security concerns in LLM applications, including prompt injection, PII handling, and data leakage risks;
• Solid experience with Vector DBs, orchestration and durable execution frameworks, and LLM APIs;
• Experience building APIs, services, and data retrieval pipelines such as RAG and vector search;
• Deep proficiency with Python for data and ML engineering, SQL, and major cloud providers;
• Extensive background in traditional ML engineering;
• Deep understanding of architecting and building reliable, scalable data systems for production use;
• Ability to influence Product, Design, and Engineering teams and align stakeholders on decisions;
• Strong product instincts and a user-focused approach to building AI features;
• Deep understanding of LLMOps, data retrieval, prompt and context engineering, and production model evaluation;
• Ability to reason about data quality, architecture, and retrieval without constant support from a dedicated data engineer;
• Ability to navigate ambiguity, autonomously scope solutions, and build required tooling;
• Ability to explain complex AI trade-offs clearly to highly technical and commercially focused stakeholders;
• Experience owning complex initiatives with organisation-wide impact beyond building and shipping;
• English is the company language and applications must be submitted in English;
• Nice to have: experience with GCP, BigQuery, Airflow, AWS, Kotlin, Javascript, Typescript, and Kubernetes.

• Remote, hybrid, or in-person setup is available in listed locations, with physical presence and valid right to work required in the chosen country;
• Visa sponsorship is not available;
• Pleo card provided;
• Catered meals or a lunch allowance for work days;
• Comprehensive private healthcare, with coverage options depending on location;
• 25 Days of holiday plus public holidays;
• Free mental health and well-being support through MyndUp;
• Paid parental leave;
• The interview process includes an intro call, technical screening, system design interview, live coding interview, Hiring Manager interview, and final leadership interview.