Pleo is investing heavily in AI-powered features across the product. You will be part of the GenAI Core team which is responsible for the horizontal platform infrastructure that makes this possible. They look after LLM routing, MCP servers, vector search infrastructure, evaluation frameworks, and agentic tooling.
This is a hands on backend/platform engineering role at the intersection of distributed systems and modern AI engineering. You will help design, build, and operate the shared AI infrastructure used by product teams across Pleo, with a strong focus on reliability, observability, security, and developer experience.
Who you'll be working with and reporting toYou'll be reporting to the Engineering Manager for the GenAI Platform team and will be working closely with senior and staff Engineers in GenAI Core. You will also collaborate with Applied AI Engineers, Data Scientists, and product engineering teams across the business.
What you'll be doingDesign, build, and operate core GenAI platform components used by product teams at Pleo, including LLM routing gateway, vector search and RAG infrastructure, tool registry and MCP gateway, AI observability and evaluation tooling (tracing LLM calls, supporting human and automated evaluation, detecting drift, and tracking costs) and infrastructure for multi-step, long-running agentic workflows.
Own production quality delivery of platform features, from design through rollout, monitoring, and follow up.
Contribute to resilient system design: sensible APIs, failure handling, rate limiting, retries, idempotency, and safe change management.
Improve reliability and observability through metrics, dashboards, alerting, incident follow ups, and operational improvements.
Partner with Applied AI Engineers and product teams to understand platform needs and help them build AI powered features safely.
Build internal SDKs, templates, and guardrails that let product engineers build AI features without needing deep infrastructure expertise.
Support other engineers through pairing, code reviews, technical feedback, and clear documentation.
Help evaluate build vs buy decisions in the rapidly evolving LLMOps tooling landscape.
Strong backend/systems engineering background, with experience building and operating production services with reliability and observability requirements.
Experience designing and delivering shared platform or infrastructure components used by multiple teams.
Strong production ownership: monitoring, alerting, incident response, debugging, and post incident learning.
Distributed systems fundamentals, including async workflows, idempotency, consistency tradeoffs, and designing for failure.
Hands on experience with LLM APIs or strong interest in learning their production failure modes: rate limits, context windows, multi vendor routing, latency variance, and cost control.
Security mindset for AI systems, including prompt injection risks, PII in logs, data leakage, and safe credential handling.
Strong programming experience in either a JVM based language or Python. We operate a polyglot platform with components written in both Kotlin and Python, and you'll be expected to contribute to both.
Clear communication and collaboration skills, especially when working with product teams and other engineers to turn ambiguous platform needs into practical solutions.
This role is a good fit for you if:
You are passionate about developer experience and get excited about being a force multiplier for engineering teams.
You have moved past prototyping and have a deep understanding of the realities of LLMOps, data retrieval, prompt and context engineering, as well as model evaluation in production.
You understand both the engineering and the data side of things, and are comfortable switching languages or technologies to achieve your goals.
This role is not a good fit for you if:
You are primarily interested in model research or algorithm development. This role is about building the tooling that enables product teams to ship AI features to production.
You prefer building customer facing features. Your key users will be other Pleo Engineers.
You cannot explain AI trade offs clearly to non technical stakeholders. You will regularly work with Product Managers, Designers, and business leaders who need to understand what is and isn't possible.
Develop a clear picture of how AI features are currently being built at Pleo and where the biggest infrastructure bottlenecks are.
Take ownership of a core platform component such as the LLM gateway, RAG infrastructure, MCP gateway, or evaluation framework, and improve its reliability, observability, or developer experience.
Deliver production ready improvements with clear rollout plans, monitoring, and operational documentation.
Partner with Applied AI Engineers and product teams to identify platform investments that would accelerate their work.
Contribute to Pleo's internal standards for AI feature development: how we evaluate quality, manage prompts, and monitor production AI systems.
Please note: We can hire on a remote, hybrid or in person set up in any of the locations listed on the advert but you will need to be physically based in the country of your choice with a valid right to work.
We are unable to offer visa sponsorship for this role.
Show me the benefits!Your own Pleo card (no more out of pocket spending!)
Lunch is on us for your work days - enjoy catered meals or receive a lunch allowance based on your local office
Comprehensive private healthcare - depending on your location, coverage options include Vitality, Alan or Médis
We offer 25 days of holiday + your public holidays
For our Team, we offer both hybrid and fully remote working options
We use MyndUp to give our employees access to free mental health and well being support with great success so far
Paid parental leave - we want to make sure that we're supportive of families and help you feel that you don't have to compromise your family due to work