Описание:
Пleo builds spend management solutions that help finance teams and employees manage business spending more seamlessly and effectively.
Задачи:
- Design, build, and operate core GenAI platform components, including an LLM routing gateway, vector search and RAG infrastructure, tool registry and MCP gateway, AI observability and evaluation tooling, and infrastructure for long-running agentic workflows;
- Own production-quality delivery of platform features from design through rollout, monitoring, and follow-up;
- Contribute to resilient system design with 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 for product engineers;
- Support other engineers through pairing, code reviews, technical feedback, and clear documentation;
- Help evaluate build-versus-buy decisions in the LLMOps tooling landscape;
- Develop a clear picture of how AI features are built at Pleo and identify infrastructure bottlenecks;
- Take ownership of a core platform component and improve its reliability, observability, or developer experience;
- Deliver production-ready improvements with rollout plans, monitoring, and operational documentation;
- Partner with Applied AI Engineers and product teams to identify platform investments;
- Contribute to Pleo's internal standards for AI feature development, quality evaluation, prompt management, and production monitoring.
Требования:
- Strong backend and 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, including monitoring, alerting, incident response, debugging, and post-incident learning;
- Knowledge of distributed systems fundamentals, including asynchronous workflows, idempotency, consistency trade-offs, and designing for failure;
- Hands-on experience with LLM APIs or strong interest in learning about 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 a JVM-based language or Python, with the ability to contribute to Kotlin and Python components;
- Clear communication and collaboration skills for turning ambiguous platform needs into practical solutions;
- Passion for developer experience and enabling engineering teams;
- Deep understanding of LLMOps, data retrieval, prompt and context engineering, and model evaluation in production;
- Ability to work across languages and technologies to achieve goals;
- Ability to explain AI trade-offs clearly to non-technical stakeholders;
- Proven experience building platforms or tooling for agentic AI;
- Ability to work fully autonomously on an entire product feature from design to implementation;
- Candidates primarily interested in model research or algorithm development are not a fit;
- Candidates who prefer building customer-facing features are not a fit.
Условия:
- Remote, hybrid, or in-person work options are available depending on the location;
- The employee must be physically based in the chosen country with a valid right to work;
- Visa sponsorship is not available;
- Pleo card provided;
- Catered meals or a lunch allowance is available for work days;
- Comprehensive private healthcare is provided 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;