GenAI Platform Engineer

Join our team as a GenAI Platform Engineer, where you will play a crucial role in building and scaling the platform capabilities that enable teams across the company to develop, deploy, and operate LLM-powered applications. You will work on platform capabilities that can be reused across different teams and business use cases, helping engineers move faster without having to solve the same infrastructure problems repeatedly. This is a highly technical role at the intersection of platform engineering, distributed systems, and GenAI.

Responsibilities

• Contribuer à la construction et à l'évolutivité des capacités de la plateforme qui permettent aux équipes de développer, déployer et exploiter des applications alimentées par des LLM.
• Développer des outils et des infrastructures qui améliorent l'expérience des développeurs pour la construction, les tests, le déploiement et l'exploitation des systèmes GenAI.
• Travailler en étroite collaboration avec les équipes d'ingénierie pour comprendre leurs cas d'utilisation et transformer les exigences communes en capacités de plateforme réutilisables.
• 4+ years of professional experience in Platform Engineering, DevOps, Data Platform Engineering, MLOps, Backend Engineering, ML Engineering, or a similar role
• You have a good understanding of LLM application architectures, including concepts such as tool calling, RAG, agent workflows, model gateways, and evaluation

Requirements

• You can diagnose and resolve issues related to reliability, latency, scalability, cost, and deployment of GenAI systems
• You have hands-on experience on Linux system administration, both in cloud and on-premises environments
• You are a strong team player with good communication skills and can explain technical trade-offs to different audiences
• Experience with observability tools such as Prometheus, Grafana, Kibana, or similar
• You have experience on DevEx and paving the SDLC for users setting up applications on top of your platform
• You have strong engineering skills, including version control, coding best practices, debugging, testing, and production readiness
• You have hands-on experience building or operating LLM-powered applications, agents, or GenAI platforms in production
• You are comfortable collaborating with cross-functional teams and helping define standards and best practices for building and operating GenAI systems
• Strong platform engineering experience with Kubernetes, Helm, Argo CD, and GitOps practices
• You understand the importance of security, access control, data privacy, and governance when building shared AI platform capabilities
• You are proficient in Python and comfortable working with backend services and APIs
• You have an experimental mindset and are comfortable launching early, learning from usage, and iterating quickly
• You have experience working with MCPs

Preferred

• Experience with LLM gateways and model abstraction layers such as LiteLLM, including routing, fallbacks, rate limits, cost controls, and multi-provider setups
• Experience with high-performance LLM serving frameworks such as vLLM, including GPU-backed inference, batching, throughput optimization, and serving OpenAI-compatible APIs is a plus
• Experience with LLM observability and evaluation tooling such as Langfuse, including tracing, prompt/version tracking, latency and cost monitoring, and production debugging