On-Device ML Engineer — Mobile AI Inference & Optimization

Unity Technologies

United States

Remote

USD 218,000 - 284,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Health insurance
Commute subsidy
Stock ownership
Retirement plans

Job summary

Unity Technologies is seeking a Senior Machine Learning Engineer for On-Device & Mobile AI to optimize multi-modal models and run them fast on phones, tablets, and desktops. You will own export, quantization, kernel tuning, and integration with the game engine to achieve interactive frame rates within strict memory and power budgets.

You will work with WebGPU/WGSL, ONNX Runtime Web, CoreML, TFLite, and diffusion/vision-language workloads, shaping latency, quality, and battery impact of AI

Qualifications

  • 5+ years in software/ML engineering, with on-device inference or real-time systems.
  • Experience deploying transformer- and/or diffusion-based models on mobile/desktop hardware — shipped, not prototype.
  • Hands-on with at least one major inference runtime and knowledge of fusion, memory layout, and runtime scheduling.
  • Low-level performance engineering with GPU/compute APIs and profiling tools.
  • Familiarity with mobile SoCs and desktop GPUs; strong Python for pipelines; familiarity with browser runtimes is a plus.

Responsibilities

  • Optimize and deploy large models for on-device inference across mobile and desktop platforms.
  • Own export, graph transformation, operator fusion, memory layout, and hardware-specific tuning.
  • Apply quantization, pruning, distillation to meet latency and memory budgets and validate against quality bars.
  • Write/tune WGSL shaders and relevant native kernels; profile with browser/platform tools to remove bottlenecks.
  • Collaborate with research and platform teams to ship robust on-device ML features.

Skills

On-device inference
Transformer models
WebGPU WGSL
Quantization
C++/ObjC/Swift
Python
Model export
Performance profiling

Tools

ONNX Runtime
CoreML
TFLite
ExecuTorch
Vulkan

Job description

Unity Technologies is seeking a Senior Machine Learning Engineer for On-Device & Mobile AI to optimize multi-modal models and run them fast on phones, tablets, and desktops. You will own export, quantization, kernel tuning, and integration with the game engine to achieve interactive frame rates within strict memory and power budgets.

You will work with WebGPU/WGSL, ONNX Runtime Web, CoreML, TFLite, and diffusion/vision-language workloads, shaping latency, quality, and battery impact of AI

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

On-Device ML Engineer — Mobile AI & Optimization
On-Device ML Engineer — Mobile AI & Optimization

Unity • San Francisco (CA)

On-site
USD 180,000 - 240,000
Senior On-Device ML Engineer — Real-Time Game AI
Senior On-Device ML Engineer — Real-Time Game AI

Unity Enterprise • San Francisco (CA)

Hybrid
USD 218,000 - 284,000
Health insurance
Stock options
Retirement plan
+7
Staff ML Engineer: On-Device AI for Real-Time Games
Staff ML Engineer: On-Device AI for Real-Time Games

Unity • Mountain View (CA)

On-site
USD 180,000 - 280,000
Senior On-Device ML Engineer for Real-Time Multimodal AI
Senior On-Device ML Engineer for Real-Time Multimodal AI

LE130 Unity Technologies SF • United States

Remote
USD 218,000 - 284,000
Health and life insurance
Commuter subsidy
Employee stock ownership
+8
Lead On-Device AI Inference Engineer for Next-Gen Games
Lead On-Device AI Inference Engineer for Next-Gen Games

LE130 Unity Technologies SF • Mountain View (CA)

On-site
USD 260,000 - 380,000
Principal On-Device AI Engineer for Real-Time Game Inference
Principal On-Device AI Engineer for Real-Time Game Inference

Unity • Mountain View (CA)

On-site
USD 190,000 - 270,000
Principal On-Device AI Engineer – Real-Time Game Inference
Principal On-Device AI Engineer – Real-Time Game Inference

Unity Technologies • Mountain View (CA)

On-site
USD 278,100 - 417,100
Comprehensive health, life, and disability insurance
Employee stock ownership
Competitive retirement/pension plans
+1
Principal Machine Learning Engineer
Principal Machine Learning Engineer

LE130 Unity Technologies SF • Mountain View (CA)

On-site
USD 260,000 - 380,000
Principal Machine Learning Engineer
Principal Machine Learning Engineer

Unity • Mountain View (CA)

On-site
USD 190,000 - 270,000
Senior ML Infrastructure Engineer – Online Inference
Senior ML Infrastructure Engineer – Online Inference

Unity Technologies • United States

Remote
USD 165,000 - 210,000
Health benefits
Stock options
Vacation & personal days
+1