Skip to content

Senior Principal Model Bring-up Engineer

SambaNovaAustin, Texas, United States; San Jose, California, United StatesOn-Site

Estimated salary, not published by the employer: Est. $207k–311k/yr

Needs a free Superjobs account. You'll finish on SambaNova's site.

Skill score

Summary

This role brings new open-weight LLM architectures up on SambaNova's RDU dataflow accelerators, covering model adaptation, multi-chip mapping, compilation, numerical validation and production serving. It also builds shared inference features such as batching, speculative decoding and FP8/FP4 so each new model is cheaper to bring up.

Function
Development
Estimated salary
Est. $207k–311k/yr
Estimated for a staff-level role, ~8 yrs experience, United States. Not published by the employer.
Work mode and location
On-Site, Austin, Texas, United States; San Jose, California, United States
Experience
8+ yrs

Job description

Overview

We take frontier open-weight models (dense, mixture-of-experts with hundreds of experts, hybrid Mamba/attention, sliding-window attention, multi-token prediction) from Hugging Face to production serving on SambaNova's RDU dataflow accelerators. That means compiling them, proving them numerically correct against the reference, serving them with the full feature set, and merging the work into a shared stack so the next model is cheaper.

You will bring new open-weight LLMs, including dense, mixture-of-experts, and hybrid Mamba/attention architectures, up on SambaNova’s RDU dataflow accelerators and into production serving. That means adapting the model, mapping it across chips and hosts, compiling it, and validating it numerically against the reference. You also build inference features like continuous batching, speculative decoding, and FP8/FP4 as shared modules, so each new model costs less to bring up.

Roles and responsibilities

  • Bring up new LLM architectures end to end: model adaptation, checkpoint conversion, multi-chip / multi-host mapping, compile, strict numerical validation, production serving with latency / throughput numbers.
  • Build inference features once as shared modules: continuous batching over a paged KV pool, prompt caching, chunked and incremental prefill, dynamic tensor shapes, speculative decoding (EAGLE-3, drafters, MTP), FP8 / FP4, tensor and expert parallelism.
  • Debug where model, compiler and hardware meet; land each fix in the right shared component.

Skills required

Top skills

  • PyTorch internals
  • Python
  • C++
  • Transformer inference

All skills (14)

  • KV caching
  • MoE routing
  • Speculative decoding
  • Accelerator bring-up
  • ML compilers
  • Inference engines
  • Numerical debugging
  • Bazel
  • Slurm
  • Dataflow compilers
  • Kernel DSLs
  • FP8 and FP4 inference
  • Mamba and SSMs
  • Expert parallelism

Qualifications

  • B.S. in Computer Science, Electrical Engineering, or 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 vs decode, batching, and speculative decoding
  • Hands-on experience with accelerator bring-up, ML compilers (MLIR, XLA, TVM, Triton, torch-mlir), or inference engines (vLLM, SGLang, TensorRT-LLM)
  • Rigor in numerical debugging
  • Comfort with Bazel, Slurm, and large monorepos
  • Clear writing and evidence-backed claims

Nice to have

  • M.S. or Ph.D. in Computer Science, Electrical Engineering, or 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

Other details

Own a model family from first compile to served and merged; turn a one-model fix into a shared module others adopt; measurably shorten one long loop for the team.

Compensation

Base Salary Range

Base Pay Range

$208,000—$312,000 USD

Hiring process

Submission Guidelines

Please note that in order to be considered an applicant for any position at SambaNova Systems, you must submit an application form for each position for which you believe you are qualified.

Benefits

Benefits Summary for US-Based, Full-Time Employment Positions

SambaNova offers a competitive total rewards package, including the base salary, plus equity and benefits. We cover 95% premium coverage for employee medical insurance, and 77% premium coverage for dependents and offer a Health Savings Account (HSA) with employer contribution. We also offer Dental, Vision, Short/Long term Disability, Basic Life, Voluntary Life, and AD&D insurance plans in addition to Flexible Spending Account (FSA) options like Health Care, Limited Purpose, and Dependent Care. Our library of well-being benefits available to you and your dependents includes a full subscription to Headspace, Gympass+ membership with access to physical gyms, One Medical membership, counseling services with an Employee Assistance Program, and much more.

Company info

SambaNova provides an AI platform offering fast AI inference, fine-tuning, and scalable solutions for agentic AI that integrate into existing data center infrastructure. The sources do not state which specific customers or user groups use the platform.

More jobs at SambaNova