Staff Design Engineer - TPU/GPU Design

OXMIQ Labs Inc.
Campbell, CA, United States
4 days ago
Apply on www.juju.com
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
5 years minimum
Working hours
Regular working hours
Job source

Tech stack

Adobe InDesign Artificial Intelligence Nvidia CUDA Computer Engineering Software Debugging Logic Synthesis of Circuits Electronic Design Automation Emulators Firmware Formal Verification Field-Programmable Gate Array (FPGA) Performance Tuning
+10 more
System on a Chip SystemVerilog Verilog Graphics Processing Unit (GPU) Application Specific Integrated Circuits Pytorch Claude Code Parallel Computation Physical Design MLIR (Multi-Level Intermediate Representation)

Job description

We are looking for a Staff Design Engineer to join our GPU/AI accelerator development team. You will play a key role in the architecture, RTL design, integration, and verification of high-performance TPU/GPU compute engines.

The ideal candidate has strong experience designing complex hardware blocks for GPUs, TPUs, AI accelerators, or other high-performance processors, with a deep understanding of processor pipelines, parallel computing, memory systems, and SoC interconnects.

Responsibilities

  • Define and implement microarchitecture for GPU/TPU compute engines and accelerator blocks
  • Develop high-quality, synthesizable SystemVerilog/RTL
  • Analyze performance, area, power, and timing tradeoffs and drive design optimization
  • Develop block-level and system-level verification strategies and debug complex hardware issues
  • Collaborate closely with architecture, verification, physical design, firmware, and software teams
  • Participate in design reviews and drive technical decisions across multiple engineering teams
  • Contribute to pre-silicon performance modeling, benchmarking, and post-silicon debug

Requirements

  • 5-10 years of experience in ASIC/SoC design or related semiconductor development
  • Strong experience with SystemVerilog/Verilog RTL design
  • Experience with one or more of:
  • Tensor/matrix processing
  • Strong understanding of digital design fundamentals, computer architecture, and performance optimization
  • Experience with industry-standard EDA tools and RTL simulation/debug
  • Ability to independently own a complex design block from microarchitecture through RTL, verification, and tapeout

Preferred Qualifications

  • Experience with NVIDIA/AMD/Google TPU or similar GPU/AI accelerator architectures
  • Experience with performance modeling and workload-driven architecture optimization
  • Familiarity with CUDA, PTX, MLIR, PyTorch, or other AI software stacks
  • Experience with formal verification, emulation, FPGA prototyping, or advanced simulation environments
  • Experience working on complex SoCs from architecture through silicon

Education

BS/MS/PhD in Computer Engineering, Electrical Engineering, or a related field - or equivalent practical experience.

This is a hands-on, individual-contributor role based on-site at OXMIQ’s Bay Area headquarters, working closely with architecture, verification, physical design, firmware, and software teams to take compute engine designs from microarchitecture through tapeout. This role requires eligibility to work in the United States. AI-assisted development tools (Claude Code or equivalent) are a standard part of engineering practice at OXMIQ and are expected in daily work.

Benefits & conditions

OXMIQ offers a competitive compensation package, including base salary, equity participation, comprehensive medical, dental, and vision coverage, and the opportunity to contribute to foundational silicon and software technology.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.juju.com
Prepare application

Good distractions

Loading talks and stories from around this role…