Teams at SPREEAI

Build and operate scalable AI infrastructure for multimodal model training and inference. Responsibilities include developing model-serving APIs, distributed GPU systems, backend services, deployment automation, observability, reliability improvements, and performance and cost optimization. The engineer will partner with applied science teams to productionize generative and vision models while improving platform usability and scalability.

Lead the design and operation of SPREEAI’s ML platform, including training workflows, model deployment, inference serving, GPU infrastructure, observability, evaluation, and production monitoring. Establish reliable research-to-production pipelines, model governance, SLOs, rollback strategies, and performance optimization across distributed systems. Partner with research, product, and engineering teams to deliver scalable, cost-efficient multimodal AI systems for real-time virtual try-on experiences.

Build and maintain React interfaces and own the Go or Node.js backend services supporting partner-facing applications. Design REST APIs, authentication, webhooks, and database systems while ensuring performance, accessibility, testing, and polished user experiences. Collaborate directly with product and partner engineering leads to deliver features end to end, and help establish engineering practices as the team scales.