Senior Platform Software Engineer, ML Accelerators

Salary: $168,400 - 193,500 per year Requirements:

• We are looking for someone with 5+ years of non-internship professional software development experience.
• We need 5+ years of full software development life cycle experience, including coding standards, code reviews, source control management, build processes, testing, and operations.
• We are seeking experience as a mentor, tech lead, or engineering team lead.
• We require 7+ years of non-internship professional experience building functional or performance models.
• We need programming experience with C++ and/or SystemC.
• We are looking for knowledge of SoC, CPU, GPU, and/or ASIC architecture and micro-architecture.
• We prefer a bachelors degree in computer science or an equivalent background.
• We value experience analyzing data and using best practices to evaluate performance drivers.
• We prefer experience developing models that integrate with QEMU.
• We value experience developing and tuning performance models for custom silicon chips.
• We prefer experience with PyTest and GoogleTest.
• We value familiarity with modern C++ (11, 14, and similar versions).
• We prefer experience in multithreaded programming.
• We value experience with machine learning accelerator hardware and/or software.

• We build and own functional models of SoC subsystems that integrate into our full-system virtual platform for firmware, driver, runtime, and application software teams.
• We develop and improve our virtual platform infrastructure, including QEMU integration, simulation performance, build and release tooling, and customer-facing documentation.
• We design models with a focus on usability and performance so software engineers can run real workloads efficiently.
• We work directly with software teams to understand their workflows, debug platform issues, and refine the model to improve productivity.
• We drive simulation performance enhancements so the platform can support increasingly complex workloads at scale.
• We contribute to model architecture decisions by choosing the right level of abstraction and fidelity for each subsystem based on customer needs.

• AWS
• Firmware
• Hardware
• Support
• Machine Learning
• QEMU
• pytest
• Cloud
• Python

More:

We build the virtual platforms that power AWS Trainium and Inferentia chip development, creating full-system C++ and SystemC models of custom SoCs so software teams can start months before silicon arrives. Our team is small, high-impact, and operates with startup pace inside AWSs custom silicon organization. This role is based in Cupertino, CA or Austin, TX, and we offer comprehensive benefits including health insurance, 401(k) matching, paid time off, parental leave, sign-on payments, and restricted stock units, with final compensation based on experience, qualifications, and location.

last updated 37 week of 2026