About the Role We are seeking a highly skilled Physical Design Engineer with deep expertise in physical design and methodology. This individual contributor role sits within our physical design team and is central to delivering power, performance, and area (PPA) optimized datapath and interconnect solutions for next-generation AI accelerators.
You'll work closely with RTL designers to define and execute on physical design strategies. You will develop tools, flows and methodologies to increase team productivity. Your work will directly impact silicon's performance and cost efficiency, as well as the team's execution velocity and quality.
In this role, you will:- Develop, build and own tools, flows and methodologies for physical implementation
- Own physical implementation of floorplan blocks from floorplanning to final signoff
- Collaborate with RTL designers to drive optimal block implementation solutions
- Analyze and optimize design for timing, power, and area trade-offs, working in collaboration with EDA vendors and ASIC partners
Qualifications:- BS w/ 4+ or MS with 2+ years or PhD with 0-1 year(s) of relevant industry experience in physical design and methodology development
- Demonstrated success in taping out complex silicon designs
- Hands-on experience with block physical implementation and PPA convergence
- Strong coding experience with python, bazel, TCL
- Strong experience building physical design tools, flows and methodologies
- Strong understanding of microarchitecture, RTL design, physical design, circuit design, physical verification and timing closure.
- Deep familiarity with industry-standard tools and flows for physical synthesis, PNR, LEC and power estimation
Bonus:- Experience with AI or HPC-focused chips
- Experience with optimizing PPA for high performance compute cores
- Hands-on experience with top-level design methodologies
To comply with U.S. export control laws and regulations, candidates for this role may need to meet certain legal status requirements as provided in those laws and regulations.
