Principal Machine Learning Engineer

Unity Technologies SF; Mountain View (CA); On-site; USD 220,000 - 320,000; Full time

Job summary

Unity Technologies SF is seeking a Principal Engineer for On-Device AI Inference & Systems to push multi-modal models (transformers and diffusion) to run fast and small inside our runtime. You will own the end-to-end stack from export to kernel tuning and ensure interactive frame rates within fixed memory and power budgets.

You will lead optimization, participate in hardware-aware decisions, and mentor engineers while shaping a scalable on-device AI platform embedded in Unity's game engine.

Qualifications

• 8+ years in software/ML engineering, with at least 4 years on on-device / edge inference or real-time systems.
• Proven production deployment of transformer- and/or diffusion-based models on mobile or desktop environments.

Responsibilities

• Own the end-to-end optimization pipeline: model export, graph transformation, operator fusion, memory-layout planning, and hardware-specific kernel tuning across accelerators.
• Make authoritative decisions on quantization and pruning to meet latency, memory, and power budgets, validated against quality bars.
• Write and tune WebGPU compute shaders (WGSL) and native kernels (Metal, Vulkan/SPIR-V, D3D12, CUDA); profile with browser and platform tools and fix bottlenecks at op/memory bandwidth level.
• Design and own the integration between the ML runtime and the game engine: real-time scheduling, threading, memory pooling, zero-copy buffers, and frame-budget management.
• Architect inference systems handling diverse inputs and producing pixel-level outputs with real-time performance, robust to production challenges (cold starts, throttling, fragmentation).
• Build supporting tooling: model packaging, on-device fallbacks, telemetry, and automated benchmarking in CI.

Skills

On-device inference

Performance-critical systems

Transformer models

Diffusion models

Tools

WGSL (WebGPU)

Metal

Vulkan

SPIR-V

D3D12

CUDA

Chrome/Dawn GPU traces

PIX

Instruments/Metal System Trace

Nsight

RenderDoc

Job description

The opportunity

We 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 our Principal Engineer for On-Device AI Inference & Systems, you will be the foremost engineering authority on taking state-of-the-art multi-modal models (transformers and diffusion networks) and making them run fast, small, and reliably within that runtime, fully integrated into a production game engine.

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.

This role is for an engineer who is energized by the gap between a research model and a shipping, AI-based product. If you love profilers, frame captures, op-fusion, and shaving milliseconds and megabytes, this is your role.

What you'll be doing

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.

What we're looking for

• 8+ years in software/ML engineering, with at least 4 years focused on on-device / edge inference or real-time, performance-critical systems.
• Proven production deployment of transformer- and/or diffusion-based models (e.g., ViT, Stable Diffusion) on mobile, de