About Positron AI
Positron.ai specializes in developing custom hardware systems to accelerate AI inference. These inference systems offer significant performance and efficiency gains over traditional GPU-based systems, delivering advantages in both performance per dollar and performance per watt. Positron exists to create the world's best AI inference systems.
About the role
As a Lead Emulation Engineer, you will provide technical leadership for the pre-silicon validation of Positron.ai’s next-generation AI inference ASIC. You will own the end-to-end emulation strategy on the Cadence Palladium platform—architecting complex model builds, managing multi-rack partitioning, and driving the 'left-shift' of our software development. You will collaborate across RTL, DV, and Software teams to build high-performance virtual environments that prove out architectural functionality and accelerate firmware/OS bring-up months before tape-out. This role is critical to our silicon success: you will set the emulation methodology, resolve hardware-software bottlenecks at scale, and ensure our design is silicon-ready.
What you'll do
- Massive-Scale Model Architecture: Lead the partitioning and compilation of our design across a multi-rack Palladium environment, optimizing for performance and debug visibility.
- Software Enablement (Left-Shift): Create and maintain the hybrid emulation and co-simulation environments (using SCE-MI or DPI) that allow our software teams to boot OS images and run AI workloads on pre-silicon hardware.
- Full-Stack Validation: Design and execute comprehensive emulation test plans to verify high-speed interfaces (PCIe Gen 6/7, 112G+VSR, Ethernet) and complex AI memory hierarchies.
- Performance & Power Analysis: Utilize Palladium’s Dynamic Power Analysis (DPA) and throughput monitors to identify "true peaks" and performance bottlenecks that simulation cannot capture.
- Vendor Management: Act as the primary technical point of contact with Cadence R&D to troubleshoot tool issues and leverage the latest Palladium Z3 capabilities.
You'll Be Successful Here if You Have
- Deep Palladium Expertise: Extensive hands-on experience with Cadence Palladium (Z1/Z2/Z3), including advanced clocking, ICE (In-Circuit Emulation), and Virtual Interface (VIF) flows
- Complex SoC Background: A track record of emulating multi-billion gate designs where partitioning, runtime predictability, and compile efficiency were critical success factors
- Automation Mastery: Expert-level Python, Tcl, and Bash skills to build and maintain the infrastructure for automated model releases and nightly regressions
- Hardware-Software Debug Skills: Proficiency in debugging low-level firmware and kernel-level issues using Verdi, SimVision, and hardware-software co-debug tools
Minimum Requirements
- Education: BS/MS in Electrical Engineering, Computer Engineering, or Computer Science.
- Experience: 8+ years in ASIC Emulation or Verification, with significant experience on large-scale Palladium installations
- Technical Skills: Mastery of SystemVerilog, Verilog, and C/C++ for transactor development and reference modeling.
- Protocol Knowledge: Deep understanding of data center protocols including PCIe, DDR and AMBA AXI/NoC
Top Skills
What We Do
Positron delivers vendor freedom and faster inference for both enterprises and research teams, by allowing them to use hardware and software explicitly designed from the ground up for generative and large language models (LLMs).
Through lower power usage and drastically lower total cost of ownership (TCO), Positron enables you to run popular open source LLMs to serve multiple users at high token rates and long context lengths. Positron is also designing its own ASIC to expand from inference and fine tuning to also support training and other parallel compute workloads.
