Physical Design Engineer, Machine Learning

Apple • San Jose, CA

1d

About The Position

As a member of Apple’s Physical Design Machine Learning team, you will help build application processors for the next generation of Apple products. You will apply physical design expertise and machine learning skills to develop predictive models, optimization algorithms, and autonomous agents that work with internal design teams to optimize power, performance, and area (PPA). The role spans the physical design flow, including RTL and logic synthesis, floorplanning, place and route, timing, noise, power and thermal analysis, voltage drop, and design for manufacturing and yield. You will train and deploy models in production place-and-route flows, and build tools, models, and agents for autonomous or semi-assisted optimization loops using EDA tooling. The work includes a range of ML methods, from traditional models and classical optimization to graph neural networks, reinforcement learning, and LLM-based agents. You will collaborate with design, power, post-silicon, CAD, software, and machine learning teams.

Requirements

• Bachelor of Science degree or higher.
• At least 3 years of relevant industry experience.
• Experience with optimization algorithms.
• Programming experience in Python or C/C++.
• Academic or industry experience in physical design.

Nice To Haves

• Practical experience with a range of machine learning approaches, including classical/traditional models, GNNs, transformers, diffusion models, and/or reinforcement learning.
• Experience building agentic systems, LLM-based agents, tool-calling/function-calling, multi-agent orchestration, or autonomous decision-making loops.
• Experience integrating machine learning models or agents into EDA tool flows via scripting (Python/TCL) or APIs.
• Master's or PhD with relevant publications in Machine Learning and/or EDA algorithms.
• Excellent communication and organizational skills.

Responsibilities

• Apply machine learning and advanced algorithms to high-impact problems across the physical design flow, including RTL and logic synthesis, floorplanning, place and route, timing/noise/power/thermal analysis, voltage drop, and design for manufacturing and yield.
• Train and deploy models in production place-and-route flows to predict and optimize outcomes and speed convergence.
• Build tools and models for agentic systems, and develop agents and autonomous or semi-assisted optimization loops that propose, evaluate, and iterate on design changes through EDA tooling.
• Work across machine learning techniques, including traditional models, classical optimization, GNNs, reinforcement learning, and LLM-based agents.
• Collaborate with design, power, post-silicon, CAD, software, and machine learning teams.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level