SoC Virtual Platform Engineer C++ SystemC

Amazon Web Services (AWS); Austin (TX); On-site; USD 143,700 - 194,400; Full time

Job summary

Annapurna Labs (U.S.) Inc. in Austin, TX or Cupertino, CA is seeking a software engineer to build and own full-system virtual platform models for Trainium/Inferentia SoCs. You will create functional C++ and SystemC models used by firmware, drivers, and runtime teams to run real workloads before silicon arrives.

You'll work with QEMU integration, improve simulation performance, and shape model architecture based on customer needs, delivering high-impact results in a small AWS silicon team.

Qualifications

• Experience programming languages such as C/C++, Python, Java or Perl.
• 2+ years writing functional models, virtual platforms, or system-level simulations for hardware (SoCs, ASICs, GPUs, CPUs).
• Familiarity with SoC, CPU, GPU, and/or ASIC architecture and micro-architecture.
• Strong customer-focused mindset for usability, reliability, and documentation.

Responsibilities

• Build and own functional models of SoC subsystems that integrate into our full-system virtual platform.
• Design models for usability and performance for software engineers to run real workloads effectively.
• Develop and improve the virtual platform infrastructure: QEMU integration, simulation performance, build and release tooling.
• Work with software teams to understand workflows, debug issues, and tailor models to maximize productivity.
• Drive simulation performance improvements to handle increasingly complex workloads at scale.
• Contribute to model architecture decisions choosing abstraction and fidelity based on customer needs.

Skills

C/C++

Python

Java

Perl

QEMU

SystemC

TLM

PyTest

GoogleTest

Multi-threading

Tools

QEMU

SystemC

TLM

Job description

Annapurna Labs (U.S.) Inc. in Austin, TX or Cupertino, CA is seeking a software engineer to build and own full-system virtual platform models for Trainium/Inferentia SoCs. You will create functional C++ and SystemC models used by firmware, drivers, and runtime teams to run real workloads before silicon arrives.

You'll work with QEMU integration, improve simulation performance, and shape model architecture based on customer needs, delivering high-impact results in a small AWS silicon team.