LLM routing and access: a centralised LLM proxy layer (LiteLLM) that routes requests to different model providers (Azure OpenAI, AWS Bedrock, Google Gemini), with budget enforcement and rate limiting
Observability and evaluation: integrations and tooling (BrainTrust) to monitor, log, and evaluate LLM calls in production, supporting both automated evaluation and human review
Platform standards and guidance: we define how AI is done at Pleo, providing patterns, contracts, and shared components that product teams build on
Internal consulting: as product teams across Pleo adopt AI capabilities, GenAI Core will increasingly act as a technical partner, helping teams design and implement AI features correctly on top of the platform
This is software engineering work. While the domain revolves around AI infrastructure, you will spend most of your time building reliable, scalable backend systems. What you’ll be doing
In this role, you will be a force multiplier for platform quality and technical direction. - Drive the design, delivery, and evolution of the GenAI Core platform, the shared AI infrastructure used by all product teams at Pleo
Own and evolve service architecture, APIs, and integration contracts, with a high bar for reliability and observability
Set technical direction for key parts of the platform, including LLM routing, budget enforcement, observability pipelines, and evaluation infrastructure
Lead cross-team technical initiatives and act as a trusted technical partner when product teams need to build AI-powered features on top of the platform
Raise the engineering bar through strong practices: code reviews, incident follow-ups, safe change management, and resilient system design
Proactively identify and address technical debt, and guide the team through architectural decisions and migrations
Support other engineers through pairing, reviews, and technical guidance
Contribute hands-on in code. You should expect to be coding a meaningful part of the time. You’ll bring solid experience with
Designing and maintaining backend systems with strong requirements for reliability and observability
Building and operating a shared platform or infrastructure components used by multiple teams
Distributed systems fundamentals, including async workflows, idempotency, consistency, and designing for failure
API design, clear service boundaries, and integrating with external systems in a maintainable way
Observability and owning systems in production, including monitoring, alerting, incident response, and post-mortems
Strong testing practices and a high quality mindset
Clear communication and pragmatic decision-making across teams and stakeholders
Nice to have
Hands-on experience working with LLM APIs (OpenAI, Anthropic, AWS Bedrock, or similar) in a production system
Familiarity with LLM evaluation patterns such as LLM-as-judge, vector similarity, and sampling strategies
Experience building or operating proxy or routing layers for AI workloads
Your colleagues would say you
Lead by example and raise the bar with pragmatism and care
Communicate clearly, listen well, and bring people along in decisions
Enjoy breaking down complex problems, gathering input, and driving to a solution
Coach and mentor others and create space for people to grow
Prefer progress over perfection, while still caring deeply about quality
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
