Physical Design Engineer — ML-Driven EDA & Optimization

Apple Inc.; San Jose (CA); On-site; USD 150,400 - 277,600; Full time

Benefits offered by this job

Medical and dental coverage

Employee stock programs

Relocation assistance

Job summary

Apple Inc. is seeking a Physical Design Engineer specialized in Machine Learning to advance our system-on-chip design flow.

You will apply ML to optimize RTL, floorplanning, place-and-route, timing, power, and thermal analyses, collaborating with CAD, power, and software teams across Apple. You will train, deploy, and manage models within production P&R flows, exploring agents and multi-agent loops to propose improvements and speed up design convergence.

Qualifications

• BS in Electrical Engineering, Computer Science, or related field
• 3+ years of industry experience in physical design or related field
• Experience with optimization algorithms and programming in Python or C/C++
• Academic or industry background in physical design

Responsibilities

• Apply ML and optimization to physical design flows (RTL, synthesis, floorplanning, place-and-route, timing, power, thermal analysis)
• Train and deploy models into production P&R flows to predict and optimize outcomes
• Build agentic systems and multi-agent orchestration for design optimization
• Experiment with ML methods including GNNs, transformers, diffusion models, reinforcement learning
• Collaborate with design, power, CAD, software and ML teams across Apple

Skills

Optimization algorithms

Python

C/C++

Physical design

Education

Bachelor's degree in EE/CS/related

Tools

EDA tooling scripting (Python/TCL)

Job description

Apple Inc. is seeking a Physical Design Engineer specialized in Machine Learning to advance our system-on-chip design flow.

You will apply ML to optimize RTL, floorplanning, place-and-route, timing, power, and thermal analyses, collaborating with CAD, power, and software teams across Apple. You will train, deploy, and manage models within production P&R flows, exploring agents and multi-agent loops to propose improvements and speed up design convergence.