Staff Machine Learning Engineer

The opportunityWe are building the next generation of AI-driven game experiences, running generative models on-device, right where the players are — on phones, tablets, laptops, and desktops. Our games run inside a modern, browser-native runtime (built on technologies such as WebGPU and WebNN), so the models that power these experiences must be deployed and accelerated entirely within that runtime. As a Senior Machine Learning Engineer for On-Device & Mobile AI, you will take state-of-the-art multi-modal models — transformers, diffusion networks, and vision‐language models (VLMs) — and make them run fast, small, and reliably on mobile and constrained hardware.This is a deeply hands‐on role. You will own the optimization and deployment of significant parts of the inference stack — from a trained checkpoint leaving research, through export, quantization, and kernel-level tuning, to a shipped feature running inside the engine at interactive frame rates within a fixed memory and power budget. Your work directly shapes the latency, quality, memory footprint, and battery profile of AI features experienced by billions of players.This role is for an engineer who is energized by the gap between a research model and a shipping, on-device product. If you enjoy profilers, frame captures, op-fusion, and shaving milliseconds and megabytes, this is your role.What you'll be doingInference & On-Device Optimization: Own the optimisation pipeline for the models you ship: model export, graph transformation, operator fusion, memory‐layout planning, and hardware‐specific tuning across NPU, mobile GPU, and desktop/laptop GPU.Quantization, pruning, distillation: Apply INT4/INT8/FP16 quantization, weight sharing, structured/unstructured pruning, and knowledge distillation to hit hard latency, memory, and power budgets — and validate them against quality bars.Low-level performance work: Write and tune WebGPU compute shaders (WGSL) and, where relevant, native kernels (Metal, Vulkan/SPIR‐V compute, CUDA); profile with browser and platform tools (Chrome/Dawn GPU traces, PIX, Instruments/Metal System Trace, Snapdragon Profiler, Nsight, RenderDoc), and eliminate bottlenecks at the op and memory‐bandwidth level.Efficiency techniques: Dynamic resolution, token reduction, cross‐frame caching/reuse, reduced‐step diffusion samplers — as engineering levers to meet budgets on target SKUs.Runtime & Systems Integration: Work with WebGPU-targeted inference runtimes (ONNX Runtime Web, Transformers.js, WebLLM, TensorFlow.js) alongside native options (CoreML, ONNX Runtime, TFLite, ExecuTorch), extend or build glue code where off‐the‐shelf options fall short of our diffusion and VLM workloads.Engine glue: Build parts of the integration between the ML runtime and the game engine: real‐time scheduling, memory pooling, zero‐copy buffer sharing between the inference and render paths, and frame‐budget management alongside the renderer.Supporting engineering: Model packaging and asset pipelines, on-device fallbacks and SKU‐aware capability tiers, crash/quality telemetry, and automated on‐device benchmarking in CI.Research Productionization: Partner with research scientists to turn novel CV and multi‐modal architectures into implementations that are deployable, debuggable, and fast on device; provide a feedback loop into research: surface hardware constraints, op-support gaps, and cost models early.Track breakthroughs: Efficient inference (efficient attention, distillation, reduced‐step diffusion); assess pragmatically how they move latency/memory/power on our target devices.Collaboration & Engineering Quality: Contribute to engineering best practices, code‐review standards, performance‐regression gates, and on-device benchmarking methodology.Measurement culture: Track KPIs for latency, quality, memory, and power for the systems you work on across the device matrix.Partner across teams: Align your work with device‐SKU constraints and product roadmaps; mentor junior and mid-level engineers through code review, pairing, and design discussion.What we're looking for5+ years in software/ML engineering, focused on on-device/edge inference or real-time, performance-critical systems.Production deployment of transformer- and/or diffusion-based models (e.g., ViT, Stable Diffusion, CLIP/SigLIP-style encoders) on mobile, desktop, or embedded hardware — shipped, not just prototyped.Hands‐on experience with at least one major inference runtime (ONNX Runtime / ORT Web, CoreML, TFLite, ExecuTorch) and understanding of operator fusion, memory layout, and runtime scheduling.Low-level performance engineering: solid command of at least one GPU/compute API — WebGPU/WGSL, Metal, Vulkan, D3D12, or CUDA — and tooling; read frame captures and kernel traces to reason about time and memory.Model‐optimization techniques: quantization, weight sharing, pruning, distillation, with judgment to hit latency and memory budgets.Understanding target hardware: mobile SoCs (Apple Neural Engine, Qualcomm Hexagon/Adreno, ARM Mali) and/or desktop/laptop GPUs (Apple Silicon, NVIDIA, AMD, Intel).Strong Python for export pipelines and training tooling; familiarity with core languages of a browser-native runtime (TypeScript/JavaScript, WGSL) is a plus.Working fluency with the models you deploy — read an architecture, modify it, reason about trade offs.Collaborative style: clear communication, reliable delivery, willingness to support and learn from teammates.You might also haveExperience shipping world-model, neural-rendering, or real-time generative pipelines (NeRF, 3DGS, real-time diffusion, or similar) on device.Hands‐on experience deploying models through WebGPU — e.g., ONNX Runtime Web, Transformers.js, WebLLM, or TensorFlow.js, including writing/tuning WGSL compute shaders.Game-engine or real-time-graphics background (Unity, Unreal, or a custom engine; Metal/Vulkan/D3D/OpenGL ES render pipelines) – especially integrating compute workloads alongside a renderer.Contributions to open-source ML inference frameworks, runtimes, or GPU/compute libraries, especially in the WebGPU ecosystem (Dawn, wgpu, ORT Web, Transformers.js, WebLLM).Familiarity with compiler stacks (MLIR, TVM, IREE, XLA) for custom kernel generation and graph optimization.Experience with on-device benchmarking infrastructure, performance-regression CI, and device-farm matrices.Proficiency in C++/Objective‐C/Swift for runtime integration.Additional informationRelocation support is not available for this position.Work visa/immigration sponsorship is not available for this position.Salary: $167,200.00 - $250,800.00BenefitsComprehensive health, life, and disability insuranceCommute subsidyEmployee stock ownershipCompetitive retirement/pension plansGenerous vacation and personal daysSupport for new parents through leave and family-care programsOffice food snacksMental Health and Wellbeing programs and supportEmployee Resource GroupsGlobal Employee Assistance ProgramTraining and development programsVolunteering and donation matching programUnity is a proud equal opportunity employer. We are committed to fostering an inclusive, innovative environment and celebrate our employees across age, race, color, ancestry, national origin, religion, disability, sex, gender identity or expression, sexual orientation, or any other protected status in accordance with applicable law. If you have a disability that means there are preparations or accommodations we can make to help ensure you have a comfortable and positive interview experience, please let us know. #J-18808-Ljbffr