All jobsApply now
AI Accelerator Software Distinguished Engineer - Framework Integration
Ampere Computing
Portland, OR · RemoteFull-time$279,500 – $419,500 / yearly
Job details
Pay
$279,500 – $419,500 / yearly
Job type
Full-time
Work setting
Remote / Hybrid
Location
Portland, OR
Posted
Posted 2 months ago
Full job description
Hybrid role in Portland, OR. Lead end-to-end technical strategy for deep learning inference optimization across Ampere accelerator platforms.
What you will do:
- Spearhead integration of PyTorch, ONNX, and llama.cpp into Ampere's deep learning backend
- Drive full-stack acceleration from framework layers through runtime and kernel development
- Improve performance and correctness for models on serving stacks like vLLM and SGLang
- Direct hardware/software co-optimization efforts to maximize efficiency and throughput
- Shape architecture of AI accelerator software components and reference implementations
- Collaborate cross-functionally with compiler, runtime, and systems teams
- Mentor engineers and establish quality and performance standards
Qualifications
- Linux accelerator runtime and user-mode driver experience for GPUs or AI accelerators
- Familiarity with modern AI development tools (Codex, Claude Code)
Requirements
- BS in Computer Science, Engineering, or related field with 15 years experience; MS with 12 years; or PhD with 8 years
- Proven software development experience with PyTorch, ONNX, and llama.cpp
- Strong systems programming in Python and C/C++
- Demonstrated performance engineering expertise (profiling, optimization, memory analysis)
- Solid understanding of AI/ML concepts and modern architectures (Transformers, Diffusion models)
SemiconductorAI
Ready to apply?
Apply on the company siteYou’ll be taken to an external site to complete your application.