On-Device ML Engineer — Mobile AI for Games

Unity Technologies; Mountain View (CA); On-site; USD 167,200 - 250,800; Full time

Benefits offered by this job

Health insurance

Stock options

Commuter benefits

Retirement plans

Vacation and personal days

Parental leave

Snacks in office

Job summary

Unity Technologies is seeking a Senior Machine Learning Engineer for On-Device & Mobile AI to push state-of-the-art multi-modal models into fast, small, and energy-efficient form factors on mobile, tablet, and desktop devices. You will own the inference stack from export through quantization and kernel tuning, delivering a shipped feature in production.

You'll optimize for latency, memory, and power, write WGSL shaders and native kernels, and collaborate across teams to align with device SKUs

Qualifications

• 5+ years in software/ML engineering, focused on on-device/edge inference or real-time, performance-critical systems.
• Deployment of transformer- or diffusion-based models on mobile/desktop hardware — shipped, not just prototyped.
• Hands-on experience with at least one major inference runtime (ORT Web, CoreML, TFLite, ExecuTorch).
• Low-level performance engineering with GPU/compute APIs and profiling.
• Model-optimization techniques to hit latency and memory budgets.
• Understanding target mobile SoCs and/or desktop GPUs.
• Strong Python for export pipelines; familiarity with TS/JS runtimes is a plus.
• Collaborative, reliable, and willing to learn from teammates.

Responsibilities

• Own the optimization pipeline for on-device models: export, graph transforms, fusion, memory layout, and hardware tuning.
• Apply quantization, pruning, distillation to meet latency, memory, and power budgets.
• Write and tune WebGPU WGSL shaders and native kernels; profile with browser and platform tools.
• Collaborate with WebGPU runtimes and native options to deploy diffusion and VLM workloads.
• Design engine glue for real-time scheduling and memory sharing with the renderer.
• Support benchmarking, CI validation, and telemetry to improve performance.
• Mentor junior engineers and align work with product roadmaps.

Skills

On-device inference

Transformer models

Runtime deployment

GPU/compute APIs

Quantization/distillation

Python

TS/JS familiarity

Collaboration

Tools

ONNX Runtime Web

CoreML

TFLite

ExecuTorch

WGSL

Metal

Vulkan

Job description

Unity Technologies is seeking a Senior Machine Learning Engineer for On-Device & Mobile AI to push state-of-the-art multi-modal models into fast, small, and energy-efficient form factors on mobile, tablet, and desktop devices. You will own the inference stack from export through quantization and kernel tuning, delivering a shipped feature in production.

You'll optimize for latency, memory, and power, write WGSL shaders and native kernels, and collaborate across teams to align with device SKUs