SambaNova
Senior Principal Model Bring-up Engineer
$208K–$312K
Austin, Texas, United States +3 · Principal · Full-time · Posted Oct 29, 2026
- Location
- Austin, Texas, United States
San Jose, California, United States
Austin, Texas, United States
San Jose, California, United States - Experience
- 8+ years of industry experience in ML systems, inference, or compiler engineering.
- Education
- B.S. in Computer Science, Electrical Engineering, or related field.
About the job
Bring open-weight LLM architectures onto SambaNova RDU accelerators, validate and serve them in production, and develop shared inference features.
What you'll do
- Adapt, convert, map, compile, numerically validate, and production-serve new LLM architectures.
- Build shared inference modules, including batching, caching, speculative decoding, and FP8/FP4 support.
- Debug issues across models, compilers, and hardware, and contribute fixes to shared components.
What they ask for
- B.S. in Computer Science, Electrical Engineering, or a related field.
- 8+ years of industry experience in ML systems, inference, or compiler engineering.
- Strong Python and PyTorch internals experience, plus some C++; deep transformer-inference knowledge.
- Hands-on experience with accelerator bring-up, ML compilers, or inference engines.
Nice to have
- M.S. or Ph.D. in Computer Science, Electrical Engineering, or a related field.
- Experience with dataflow or spatial compilers, kernel DSLs, FP8/FP4 inference, Mamba/SSMs, expert parallelism, multi-agent AI engineering workflows, or open-source inference/compiler contributions.
Pay
$208,000 — $312,000 USD (base salary)
Tools
Python, PyTorch, C++, MLIR, XLA, TVM, Triton, torch-mlir
AI focus
Bring up and production-serve open-weight LLMs, including dense, MoE, and hybrid Mamba/attention models; build inference features for them.
Model-written summary · the original posting is authoritative