Description
Unity is hiring a Principal Engineer for On-Device AI Inference & Systems to own the end-to-end deployment and optimization of multi-modal transformer and diffusion models within a browser-native runtime integrated into a production game engine. The role covers model export, quantization, pruning, distillation, WebGPU and native GPU kernel tuning, inference runtime selection, game-engine integration, performance profiling, productionization, and engineering leadership. Candidates need 8+ years of software or ML engineering experience, including at least 4 years focused on on-device or real-time performance-critical systems, along with production experience deploying transformer or diffusion models and hands-on expertise with WebGPU, inference runtimes, GPU APIs, and model-optimization techniques. The base salary ranges from $197,400 to $325,400 depending on work location, with possible equity and incentive participation.
