The ad says“Hands-on expertise with at least one major inference runtime (ONNX Runtime / ORT Web, CoreML, TFLite, ExecuTorch) and deep understanding of operator fusion, memory layout, and runtime scheduling”
The ad says“Low-level performance engineering: strong command of at least one GPU/compute API — WebGPU/WGSL, Metal, Vulkan, D3D12, or CUDA — and the profiling tools to go with it. You can read a frame capture and a kernel trace and know where the time and memory go”
The ad says“Low-level performance engineering: strong command of at least one GPU/compute API — WebGPU/WGSL, Metal, Vulkan, D3D12, or CUDA — and the profiling tools to go with it. You can read a frame capture and a kernel trace and know where the time and memory go”
The ad says“Working knowledge of model-optimization techniques — quantization (INT4/INT8/FP16), weight sharing, pruning, and distillation — and the practical judgment to apply them to hit latency and memory budgets. You don’t need to be a research expert in these methods; you need to use them effectively as engineering tools”
The ad says“Hands-on expertise with at least one major inference runtime (ONNX Runtime / ORT Web, CoreML, TFLite, ExecuTorch) and deep understanding of operator fusion, memory layout, and runtime scheduling”
The ad says“Inference & On-Device Optimization”
The ad says“Familiarity with compiler stacks (MLIR, TVM, IREE, XLA) for custom kernel generation and graph optimization”
The ad says“Proficiency in the core languages of a browser-native runtime — TypeScript/JavaScript and WGSL — plus solid Python for export pipelines and training-side tooling”
The ad says“Low-level performance engineering: strong command of at least one GPU/compute API — WebGPU/WGSL, Metal, Vulkan, D3D12, or CUDA — and the profiling tools to go with it. You can read a frame capture and a kernel trace and know where the time and memory go”
The ad says“Familiarity with compiler stacks (MLIR, TVM, IREE, XLA) for custom kernel generation and graph optimization”
The ad says“Hands-on expertise with at least one major inference runtime (ONNX Runtime / ORT Web, CoreML, TFLite, ExecuTorch) and deep understanding of operator fusion, memory layout, and runtime scheduling”
The ad says“Working knowledge of model-optimization techniques — quantization (INT4/INT8/FP16), weight sharing, pruning, and distillation — and the practical judgment to apply them to hit latency and memory budgets. You don’t need to be a research expert in these methods; you need to use them effectively as engineering tools”
The ad says“Proficiency in the core languages of a browser-native runtime — TypeScript/JavaScript and WGSL — plus solid Python for export pipelines and training-side tooling”
The ad says“Working knowledge of model-optimization techniques — quantization (INT4/INT8/FP16), weight sharing, pruning, and distillation — and the practical judgment to apply them to hit latency and memory budgets. You don’t need to be a research expert in these methods; you need to use them effectively as engineering tools”
The ad says“Hands-on expertise with at least one major inference runtime (ONNX Runtime / ORT Web, CoreML, TFLite, ExecuTorch) and deep understanding of operator fusion, memory layout, and runtime scheduling”
The ad says“Familiarity with compiler stacks (MLIR, TVM, IREE, XLA) for custom kernel generation and graph optimization”
The ad says“Proficiency in the core languages of a browser-native runtime — TypeScript/JavaScript and WGSL — plus solid Python for export pipelines and training-side tooling”
The ad says“Low-level performance engineering: strong command of at least one GPU/compute API — WebGPU/WGSL, Metal, Vulkan, D3D12, or CUDA — and the profiling tools to go with it. You can read a frame capture and a kernel trace and know where the time and memory go”
The ad says“Hands-on experience deploying models through WebGPU — e.g., ONNX Runtime Web (WebGPU EP), Transformers.js, WebLLM, or TensorFlow.js — including writing/tuning WGSL compute shaders and working within WebGPU’s adapter, device-limits, and binding model. Equivalent deep experience with a native GPU/compute API plus a clear path to WebGPU will also be considered”
The ad says“Working knowledge of model-optimization techniques — quantization (INT4/INT8/FP16), weight sharing, pruning, and distillation — and the practical judgment to apply them to hit latency and memory budgets. You don’t need to be a research expert in these methods; you need to use them effectively as engineering tools”
The ad says“Hands-on experience deploying models through WebGPU — e.g., ONNX Runtime Web (WebGPU EP), Transformers.js, WebLLM, or TensorFlow.js — including writing/tuning WGSL compute shaders and working within WebGPU’s adapter, device-limits, and binding model. Equivalent deep experience with a native GPU/compute API plus a clear path to WebGPU will also be considered”
The ad says“Familiarity with compiler stacks (MLIR, TVM, IREE, XLA) for custom kernel generation and graph optimization”
This is a deeply hands-on, high-impact engineering role. You will own the inference and integration stack end-to-end — from the moment a trained checkpoint leaves research, through export, optimization, and kernel-level tuning, to a shipped feature running inside the engine at interactive frame rates within a fixed memory and power budget.
You will set the engineering standards, drive the architecture of the runtime and integration layers, and mentor a team of senior and mid-level engineers. Your work directly determines the latency, quality, memory footprint, and battery profile of AI features experienced by players worldwide
Inference & On-Device Optimization
Own the end-to-end optimization pipeline: model export, graph transformation, operator fusion, memory-layout planning, and hardware-specific kernel tuning across NPU, mobile GPU, and desktop/laptop GPU
Make authoritative decisions on quantization (INT4/INT8/FP16), weight sharing, structured/unstructured pruning, and knowledge distillation to hit hard latency, memory, and power budgets — and validate them against quality bars
Drive low-level performance work: write and tune WebGPU compute shaders (WGSL) and, where relevant, native kernels (Metal, Vulkan/SPIR-V compute, D3D12, 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
Apply 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
Evaluate, select, and drive adoption of WebGPU-targeted inference runtimes (ONNX Runtime Web, Transformers.js, WebLLM, TensorFlow.js) alongside native options (CoreML, ONNX Runtime, TFLite, ExecuTorch) — and extend or build runtime/glue code where off-the-shelf options fall short of our diffusion workloads
Design and own the integration between the ML runtime and the game engine: real-time scheduling, threading, memory pooling, zero-copy buffer sharing between the inference path and the render path, and frame-budget management alongside the renderer
Architect inference systems that handle diverse inputs — images, text, primitives, metadata — and produce pixel-level outputs with real-time performance, robust to the messy realities of production (cold starts, thermal throttling, device fragmentation, backgrounding)
Build the 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 closely with research scientists to turn novel architectures into implementations that are deployable, debuggable, and fast on device
Provide the feedback loop back into research: surface hardware constraints, op-support gaps, and cost models early so model design and deployment converge
Track breakthroughs in efficient inference (efficient attention, distillation, reduced-step diffusion) and assess them pragmatically: what actually moves latency/memory/power on our target devices, and what is worth the engineering cost
Engineering Leadership
Lead and mentor a team of engineers; set engineering best practices, code-review standards, performance-regression gates, and on-device benchmarking methodology
Champion a culture of measurement: define and enforce KPIs for latency, quality, memory, and power, and ensure they are tracked rigorously across the device matrix
Partner with platform engineers, product managers, and runtime teams to align ML capabilities with device-SKU constraints and product roadmaps
Benefits
Comprehensive health, life and disability insurance
Employee stock ownership
Generous vacation and personal days
Office food and free snacks, lots of health options!
Employee Resource Groups
Training and development programs
Commute subsidy
Competitive retirement/pension plans
Paid leave for new parents
Mental Health and Wellbeing programs and support
Global Employee Assistance Program
Volunteering and donation matching program
Preferred experience
Strong understanding of target hardware: mobile SoCs (Apple Neural Engine, Qualcomm Hexagon/Adreno, ARM Mali) and desktop/laptop GPUs (Apple Silicon, NVIDIA, AMD, Intel) — and how to target each for peak throughput
Hands-on experience deploying models through WebGPU — e.g., ONNX Runtime Web (WebGPU EP), Transformers.js, WebLLM, or TensorFlow.js — including writing/tuning WGSL compute shaders and working within WebGPU’s adapter, device-limits, and binding model. Equivalent deep experience with a native GPU/compute API plus a clear path to WebGPU will also be considered
Track record of technical leadership: setting engineering direction, influencing cross-functional partners, and growing engineers
Hands-on expertise with at least one major inference runtime (ONNX Runtime / ORT Web, CoreML, TFLite, ExecuTorch) and deep understanding of operator fusion, memory layout, and runtime scheduling
Proven production deployment of transformer- and/or diffusion-based models (e.g., ViT, Stable Diffusion) on mobile, desktop, or embedded hardware — shipped, not just prototyped
Working fluency with the models you deploy — enough to read an architecture, modify it for deployment, and reason about accuracy trade-offs
Working knowledge of model-optimization techniques — quantization (INT4/INT8/FP16), weight sharing, pruning, and distillation — and the practical judgment to apply them to hit latency and memory budgets. You don’t need to be a research expert in these methods; you need to use them effectively as engineering tools
Proficiency in the core languages of a browser-native runtime — TypeScript/JavaScript and WGSL — plus solid Python for export pipelines and training-side tooling
8+ years in software/ML engineering, with at least 4 years focused on on-device / edge inference or real-time, performance-critical systems
Low-level performance engineering: strong command of at least one GPU/compute API — WebGPU/WGSL, Metal, Vulkan, D3D12, or CUDA — and the profiling tools to go with it. You can read a frame capture and a kernel trace and know where the time and memory go
Experience shipping world-model, neural-rendering, or real-time generative pipelines (NeRF, 3DGS, real-time diffusion, or similar) on device
Deep 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 the WebGPU specification and its evolving compute features (subgroups, FP16/shader-f16, timestamp queries) and the trade-offs of running heavy diffusion workloads in the browser/web runtime
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 large device-farm matrices
