Software Engineer - Hardware Abstraction Layer, AWS Machine Learning Accelerators
ARCHIVED
We can't find an active application page for this role right now. It may reopen or be listed elsewhere. Use Next Steps to search for an active apply link and similar live jobs.
Overview:
In this role, you will help build the HAL that manages AWS ML SoCs like Trainium and Inferentia. You’ll collaborate with hardware designers and system software teams to design, test, and deploy a scalable HAL across multiple internal customers. You drive architecture, debugging, and cross-functional solutions to ensure chip functionality, performance, and security. This position offers a fast-paced, startup-like environment within a large organization, focused on advancing custom silicon for cloud ML servers. You will work with cross-disciplinary teams to deliver robust abstractions and tooling that simplify use of our SoCs.
Compensation / Benefitssign-on payments and RSUshealth insurance (medical, dental, vision, prescription)401(k) matchingpaid time offparental leaveEAP and mental health support
Responsibilities:
Develop HALs for new SoC IPs in collaboration with hardware designersArchitect and debug HALs; solve system-level architectural issuesContinuously test and deploy software stacks across internal customersRefactor and maintain codebases throughout the device lifecycleImprove tooling and interfaces to make SoCs easier to use by customers
Key requirements:
C++ proficiencyPython familiarity 2+ years writing functional or performance hardware models (SoCs, ASICs, GPUs, CPUs, IP blocks) Knowledge of SoC/CPU/GPU/ASIC architecture and micro-architectureExperience with modular driver architectures (Linux or Windows) Enjoy working with hardware-based systemsStrong opinions about software architectureAbility to build effective abstractions over low-level SoC detailsSystemC or TLM-based modelingDV teams or verification flow integrationCorrelation of functional models with RTL simulation or emulation