Senior ML Platform Engineer

About the role

Are you a kid at heart looking to build a career with a leading global children's toy, entertainment and digital gaming company? At Spin Master, our unwavering commitment to open mindedness, integrity and innovation is a great part of what has made us an industry leader. How do we stay ahead of the pack? By hiring the best and brightest minds—and that’s why we want you!

Hapiko, a new part of the Spin Master family, is the creator of Stickerbox, an AI sticker printer for kids. A child holds a button, says "a unicorn riding a slice of pizza through space," and seconds later, a physical sticker prints out. This is powered by a proprietary generation pipeline that turns a child's idea into safe, fun, printed art in just a few seconds.

You will own the architecture and performance of the machine learning pipeline that powers Stickerbox, scaling this technology to support a global product launch. This role is designed for a builder who wants to learn exactly how to launch and scale a physical AI product for kids from the ground up. You will make the foundational architectural decisions and translate product requirements into reality.

Responsibilities

• Own end-to-end latency from a kid's voiced input to a physical printed sticker, and the profiling to eliminate every bottleneck
• Design and manage model deployment, versioning, and rollback strategies for a fleet of consumer hardware devices
• Optimize batching, caching, and GPU utilization across image generation, speech recognition, and character models to keep the experience fast and affordable
• Conduct build-vs-buy analysis for hosting and inference architecture and lead any resulting migrations
• Design and maintain serving-side enforcement of product safety, kid-safe compliance, and automated character-fidelity checks
• Manage the queues, autoscaling, observability, and release engineering that supports the ML generation path

Skills and experience

• Experience deploying and operating diffusion or similar generative ML models in production with real latency constraints
• Experience profiling a generation path to optimize for performance and cost
• End-to-end production ownership experience, including deployment, capacity planning, observability, and on-call support
• Advanced knowledge of ML infrastructure, inference systems, and production software architecture
• Experience translating product requirements into scalable technical solutions and roadmaps
• Experience with consumer hardware, on-device/edge inference, ASR, or child-directed digital products is a strong plus

Pay

The anticipated pay range for candidates who will work in New York City is $166,100 to $221,400 per annum. The offered pay to a successful candidate will be dependent on several factors that may include but are not limited to years of experience within the job, years of experience within