Senior Performance Modeling Engineer, AI Inference Deployments

Positron Corporation
•$220,000 - $270,000•Remote

About The Position

The Senior Performance Modeling Engineer owns tools that help customers understand how AI models will run on Positron hardware at scale, including chip requirements, expected throughput and latency, and comparisons with GPUs and other accelerators. The role works with customers, product, and the chip modeling team to turn deployment questions into quantified, actionable estimates. The work spans analytical modeling, simulation, and real hardware measurements. The engineer builds deployment-level models on top of chip performance simulators, validates projections against hardware, and packages results in a tool customers can run themselves. Two engineers are being hired: one will take primary responsibility for modeling architecture, while the other will focus on per-model deployment studies and the customer-facing tool.

Requirements

  • At least 5 years of experience in performance modeling, capacity planning, or systems architecture for large-scale AI inference, HPC, or data-center systems.
  • Demonstrated experience building analytical or queueing performance models and calibrating them against measured systems.
  • Deep systems-level understanding of LLM inference, including prefill versus decode, KV cache, parallelism strategies, mixture-of-experts routing, batching, time-to-first-token, and tokens per second.
  • Working knowledge of data-center networking, including latency, bandwidth, and topology, and GPU performance characteristics.
  • Ability to work with incomplete information, state assumptions explicitly, and provide estimates with error bars.
  • Strong Rust skills, or expert-level C/C++ skills and willingness to work in Rust day to day.
  • Proficiency in Python for analysis, experiments, and visualization.
  • Excellent communication skills and ability to explain sizing results, their drivers, and their reliability to engineers and customers.
  • Currently authorized to work in the U.S.; new visa sponsorship is not available, though H-1B transfers may be facilitated for eligible candidates.

Nice To Haves

  • Hands-on experience sizing or benchmarking inference deployments across many accelerators in production.
  • A track record of building customer-facing performance or total-cost-of-ownership tools.

Responsibilities

  • Partner with customers and product to turn deployment questions into focused studies with clear assumptions, options, metrics, and recommendations.
  • Run apples-to-apples comparisons of deployments on competitor hardware and explain the factors behind performance differences.
  • Design and deliver a standalone performance-estimation tool that customers can run on their own workloads.
  • Model large-scale inference deployment topologies, including tensor, pipeline, expert, and data parallelism, batching, context length, and mixed Positron-plus-GPU configurations.
  • Model network and system characteristics, including interconnect latency and bandwidth, redundancy, and throughput limits as chip count grows.
  • Develop and extend analytical and simulation-based deployment models that consume the chip performance simulator, ensuring estimates trace back to a shared hardware model.
  • Validate projections against measured hardware runs and keep models calibrated as chips, software, and workloads evolve.

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