Senior Principal Model Bring-up Engineer
About The Position
SambaNova is a leader in next-generation AI infrastructure, delivering a full-stack inference platform to customers worldwide. Its Reconfigurable Dataflow Unit (RDU) is built on a dataflow architecture and is packaged into SambaRack rack-scale hardware. The role brings new open-weight large language models—including dense, mixture-of-experts, and hybrid Mamba/attention architectures—from initial adaptation through production serving on SambaNova RDU dataflow accelerators. Work includes mapping models across chips and hosts, compiling them, and validating their numerical correctness against reference implementations. The engineer also develops reusable inference features as shared modules so future model bring-up requires less effort. The team works with frontier open-weight models, compiling them, proving numerical correctness, enabling their serving features, and integrating the work into a shared stack. Success in the first six months means owning a model family from first compile through serving and integration, turning a model-specific fix into a shared module adopted by others, and measurably shortening a lengthy team workflow.
Requirements
- 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, including KV caching, GQA and sliding-window attention, MoE routing, prefill versus decode, batching, and speculative decoding.
- Hands-on experience with accelerator bring-up, ML compilers (MLIR, XLA, TVM, Triton, or torch-mlir), or inference engines (vLLM, SGLang, or TensorRT-LLM).
- Rigor in numerical debugging.
- Comfort with Bazel, Slurm, and large monorepos.
- Clear writing and evidence-backed claims.
Nice To Haves
- M.S. or Ph.D. in Computer Science, Electrical Engineering, or a related field.
- Experience with dataflow or spatial compilers.
- Experience with kernel DSLs.
- Experience with FP8 and FP4 inference.
- Experience with Mamba and SSMs.
- Experience with expert parallelism.
- Experience with multi-agent AI engineering workflows.
- Open-source inference or compiler contributions.
Responsibilities
- Bring up new LLM architectures end to end, including model adaptation, checkpoint conversion, multi-chip and multi-host mapping, compilation, strict numerical validation, and production serving with latency and throughput measurements.
- Build reusable inference features as shared modules, including continuous batching over a paged KV pool, prompt caching, chunked and incremental prefill, dynamic tensor shapes, speculative decoding, FP8/FP4, and tensor and expert parallelism.
- Debug issues at the intersection of models, compilers, and hardware, and land each fix in the appropriate shared component.
- Own a model family from first compile through serving and integration into the shared stack.
- Turn model-specific fixes into shared modules and measurably shorten a lengthy team workflow.
Benefits
- Competitive total rewards package including base salary, equity, and benefits.
- 95% premium coverage for employee medical insurance and 77% premium coverage for dependents.
- Health Savings Account (HSA) with employer contribution.
- Dental, vision, short- and long-term disability, basic life, voluntary life, and AD&D insurance plans.
- Flexible Spending Account (FSA) options for health care, limited purpose, and dependent care.
- Well-being benefits including Headspace subscription, Gympass+ membership, One Medical membership, counseling services, and an Employee Assistance Program.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
