ML Systems Engineer, Model Architectures

Positron.ai

15m ago • Remote

Mid

Remote

160,000 - 350,000 USD/yr

  1. Select offer
  2. Add resume
  3. Analyze
  4. Improve
  5. Apply
  6. Auto-send · soon

Match your resume with similar open roles

Upload your resume to automatically match with active openings similar to this role.

PDF up to 10 MB

Your resume is private & secure

Resume Checker & Builder preview

Potential salary for ML Systems Engineer, Model Architectures role

Improve your resume now

$160,000 – $350,000/year

Quick Facts

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

Description

You will be the first engineer to run new model architecture variants on dedicated hardware—starting in simulation before RTL or silicon exists. You’ll implement and verify inference components (operators, numerics, memory layouts) bit-exactly against reference frameworks, then expand simulator coverage across prefill/decode and key transformer features. You’ll also drive automation for customer model bring-up to reduce turnaround time.

Responsibilities

  • Implement operators, numerics, and memory layouts in the simulator with bit-exact matching to references
  • Extend simulator coverage across the full inference path (prefill/decode), including embeddings, attention variants, Mixture-of-Experts routing, and quantized formats
  • Maintain reference comparisons and regression coverage as simulators and hardware evolve
  • Evaluate new architectures before hardware exists by identifying compute, memory, and data-movement requirements
  • Bring up customer models in simulation and own turnaround time; automate the end-to-end bring-up workflow with agentic tooling

Requirements

  • 4+ years of experience as an ML systems or inference engineer
  • Strong operator-level understanding of transformer internals: attention variants, Mixture-of-Experts, embeddings, KV cache, quantization (INT8 and FP8)
  • Demonstrated experience implementing/porting inference by hand using PyTorch, llama.cpp, vLLM, TensorRT-LLM, or a custom runtime
  • Hands-on debugging of numerical mismatches against a reference down to the operator and bit
  • Ability to turn a model architecture paper into a working, verified implementation
  • Strong Rust skills, or expert-level C/C++ with willingness to work in Rust day to day; strong Python skills
  • Excellent communication skills to explain hardware needs and where the current design falls short

Benefits

  • Fully company-paid medical, dental, and vision insurance for you and dependents; life and disability coverage
  • Supplemental hospital, critical illness, and accident coverage options
  • Unlimited paid time off; 13 paid company holidays; remote-first culture with home office setup
  • Competitive salary and equity; 401(k) with company matching (eligible from day one)
  • Visa support: open to facilitating H-1B visa transfers for eligible candidates (no new sponsorship)

See similar jobs

Explore similar jobs and use your resume score to choose where to apply next

See more

Unlock Full Resume Report