ML Systems Engineer, Model Architectures (Mid/Senior/Principal)

Positron Corporation
•$160,000 - $350,000•Remote

About The Position

As an ML Systems Engineer, you will bring new model architectures up on Positron AI hardware in simulation before RTL or silicon exists. You will work with chip architects, compiler and SDK teams, and customers to understand architecture requirements and ensure the simulator executes models bit-exactly. The role is implementation-heavy, covering new attention variants, mixture-of-experts, embeddings, and quantization formats in the simulator, with verification against reference frameworks. You will establish fast turnaround for new-model bring-up and help make the process fully automated. You will evaluate new architectures before hardware exists, identifying their compute, memory, and data-movement requirements and informing potential chip changes. You will also bring customer models up in simulation ahead of emulator and hardware runs, maintaining reference comparisons and regression coverage as the simulator and hardware evolve. The role is open to candidates at mid, senior, or principal scope depending on experience. It is remote-first. Candidates must already be authorized to work in the U.S.; new visa sponsorship is unavailable, although H-1B transfers may be facilitated for eligible candidates.

Requirements

  • At least 4 years of experience as an ML systems or inference engineer.
  • Strong understanding of transformer internals at the operator level, including attention variants, mixture-of-experts, embeddings, KV cache, and INT8 and FP8 quantization.
  • Demonstrated experience implementing or porting model inference by hand in PyTorch, llama.cpp, vLLM, TensorRT-LLM, or a custom runtime.
  • Hands-on experience debugging numerical mismatches against a reference down to the operator and bit level.
  • Ability to read a model architecture paper and turn it into a working, verified implementation.
  • Strong Rust skills, or expert-level C/C++ skills and willingness to work in Rust day to day.
  • Strong Python skills for model and reference work.
  • Excellent communication skills, including the ability to explain architecture hardware requirements and where the current design falls short.
  • Current authorization to work in the U.S.; new visa sponsorship is not available.

Nice To Haves

  • Experience mapping models onto accelerator hardware or writing kernels for a non-GPU architecture.
  • Prior experience serving as the technical point of contact for customer model requests.

Responsibilities

  • Implement simulator operators, numerics, and memory layouts required by new model architectures, with bit-exact results against reference implementations.
  • Extend simulator coverage across the inference path, including prefill and decode, embeddings, grouped-query, gated, linear, and sparse attention variants, mixture-of-experts routing, and quantized formats.
  • Maintain reference comparisons and regression coverage to preserve correctness as the simulator and hardware evolve.
  • Evaluate architectures before hardware exists, identifying compute, memory, and data-movement requirements and potential chip changes.
  • Bring customer models up in simulation before emulator and hardware runs, and own the turnaround time for doing so.
  • Partner with the agentic tooling engineer to automate new-model bring-up from model specification through simulator coverage.
  • Explain new architecture hardware requirements and design limitations to collaborators.

Benefits

  • Fully company-paid medical, dental, and vision insurance for employees and dependents.
  • Company-paid life and disability coverage, with voluntary options to add more.
  • Supplemental hospital, critical illness, and accident coverage available.
  • Unlimited paid time off.
  • 13 paid company holidays.
  • Remote-first culture with a company-provided computer and home office setup.
  • Competitive salary and equity.
  • 401(k) with company matching, eligible from day one.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service